© 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

    slice step (negative activations)

    python-code · gemini-2.5-flash-lite

    lambda argument in key function

    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
    -0.05
     given
    -0.03
     each
    -0.03
     that
    -0.03
     the
    -0.03
    ]][
    -0.03
     represe
    -0.03
     based
    -0.03
     The
    -0.03
     and
    -0.02
    Positive Logits
    da
    0.01
     %
    0.00
    &
    0.00
    #
    0.00
    '
    0.00
    *
    0.00
    %
    0.00
    )
    0.00
    !
    0.00
    "
    0.00
    Activations Density 81.390%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .t method calls

    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
    ave
    -0.07
    ush
    -0.06
    append
    -0.06
    ust
    -0.06
     representing
    -0.06
    sert
    -0.06
     given
    -0.05
    structions
    -0.05
     add
    -0.04
    ctionary
    -0.04
    Positive Logits
     break
    0.05
     other
    0.04
     between
    0.03
     algorithm
    0.03
     function
    0.03
    rint
    0.02
    .write
    0.02
     print
    0.02
    da
    0.01
     sys
    0.01
    Activations Density 25.012%

    No Known Activations