© 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

    import statement (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
     graph
    -0.16
    raph
    -0.15
    _graph
    -0.15
    .graph
    -0.14
     network
    -0.14
    etwork
    -0.14
    network
    -0.13
    loc
    -0.13
    (graph
    -0.13
    graph
    -0.13
    Positive Logits
    ars
    0.12
    rap
    0.11
    ar
    0.11
    ard
    0.11
    arch
    0.08
    ess
    0.08
    ork
    0.08
    atri
    0.08
    urn
    0.08
    ariables
    0.08
    Activations Density 99.582%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    square root argument

    python-code · gemini-2.5-flash-lite

    function call arguments (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
     route
    -0.10
    _route
    -0.09
     routes
    -0.09
    (route
    -0.08
    _city
    -0.08
    route
    -0.08
    _routes
    -0.08
    _cities
    -0.08
     city
    -0.08
    liver
    -0.07
    Positive Logits
    [str
    0.02
    _total
    0.02
    otal
    0.02
    cur
    0.02
    _string
    0.02
    _str
    0.02
    udent
    0.02
    total
    0.02
     str
    0.02
    .split
    0.02
    Activations Density 100.000%

    No Known Activations