© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 6711
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    range followed by parenthesis (negative activations)

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    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
    Not in Any Lists

    No Comments

    Negative Logits
     closest
    -0.28
    _distance
    -0.27
     distances
    -0.26
    distance
    -0.26
     distance
    -0.26
    distances
    -0.25
    _distances
    -0.25
    arest
    -0.21
    losest
    -0.21
    itude
    -0.20
    POSITIVE LOGITS
    raph
    0.12
    light
    0.12
    in
    0.11
    .edges
    0.11
    graph
    0.10
     edges
    0.10
    est
    0.10
     edge
    0.10
     Graph
    0.10
     graph
    0.10
    Activations Density 99.721%

    No Known Activations