© 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 calls on object attributes

    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
    [:
    -0.07
    &
    -0.05
     :
    -0.05
     qu
    -0.05
    qu
    -0.04
    vailable
    -0.04
     &
    -0.04
    sed
    -0.04
    ail
    -0.04
    :-
    -0.03
    Positive Logits
    h
    0.05
    _t
    0.05
     found
    0.04
    tem
    0.04
    .t
    0.03
    ithm
    0.03
     Par
    0.03
    _ch
    0.03
    ru
    0.03
    ord
    0.03
    Activations Density 19.036%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `for` loops (negative activations)

    python-code · gemini-2.5-flash-lite

    string methods (is, lower)

    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
    rect
    -0.03
    rior
    -0.03
     Returns
    -0.03
    ct
    -0.02
    ctor
    -0.02
     Output
    -0.02
     Return
    -0.01
    ck
    -0.01
    udoku
    -0.01
    (self
    -0.01
    Positive Logits
    .strip
    0.05
    .split
    0.02
    args
    0.02
    code
    0.02
    param
    0.02
    per
    0.02
    ays
    0.02
     or
    0.01
    .y
    0.01
    op
    0.01
    Activations Density 93.325%

    No Known Activations