© 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. 987
    Prev
    Next
    INDEX
    Explanations

    .height attribute access (negative activations)

    python-code · gemini-2.5-flash-lite

    re followed by dict

    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
    eight
    -0.42
     math
    -0.25
    ilename
    -0.24
     ((
    -0.23
    ax
    -0.13
    low
    -0.13
    point
    -0.13
    ct
    -0.11
     w
    -0.05
    loor
    -0.05
    POSITIVE LOGITS
     de
    0.16
    ok
    0.12
     par
    0.12
    con
    0.10
    .g
    0.10
     se
    0.08
    co
    0.08
     as
    0.08
    .p
    0.07
    um
    0.06
    Activations Density 96.477%

    No Known Activations