© 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. Residual Stream
    9. 7-RESID
    11. 1292
    Prev
    Next
    INDEX
    Explanations

    dot followed by method (negative activations)

    python-code · gemini-2.5-flash-lite

    import statements and json parsing

    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
    dule
    -0.32
    du
    -0.25
    ke
    -0.24
    ress
    -0.21
    fo
    -0.19
    ls
    -0.18
    gs
    -0.18
    89
    -0.15
    ery
    -0.14
    _state
    -0.10
    POSITIVE LOGITS
    oin
    0.24
    ine
    0.21
    ines
    0.20
    rip
    0.18
    ax
    0.15
     abs
    0.15
    tion
    0.14
    vel
    0.14
    in
    0.13
    um
    0.12
    Activations Density 96.399%

    No Known Activations