© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    Side-by-side compare needs a wider screen.
    Open other featureClose compare
    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method definition `def j(self)`

    python-code · gemini-2.5-flash-lite

    class definition parenthesis (negative activations)

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     None
    -0.03
     default
    -0.03
    ("
    -0.03
    ('
    -0.02
    \
    -0.02
     False
    -0.02
    ault
    -0.02
    ^
    -0.02
    ?
    -0.02
     "
    -0.02
    Positive Logits
    join
    0.05
     Par
    0.02
     Tuple
    0.02
    _with
    0.02
    ith
    0.01
    ()
    0.01
     whe
    0.01
     y
    0.01
     with
    0.01
     that
    0.01
    Activations Density 11.875%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    turtle module or .title()

    python-code · gemini-2.5-flash-lite

    tuple or list indexing (negative activations)

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     representing
    -0.06
     given
    -0.05
     that
    -0.04
     each
    -0.04
     the
    -0.04
    ]][
    -0.04
     represe
    -0.04
     based
    -0.03
     The
    -0.03
     and
    -0.03
    Positive Logits
    da
    0.02
     heap
    0.00
     function
    0.00
     True
    0.00
     contain
    0.00
     check
    0.00
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    Activations Density 80.983%

    No Known Activations