© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71919
    Prev
    Next
    INDEX
    Explanations

    code-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.81
    UnusedPrivate
    -0.71
    WebVitals
    -0.71
    LookAnd
    -0.65
     pinulongan
    -0.62
    GEBURTSDATUM
    -0.62
    interopRequire
    -0.59
    CPtr
    -0.59
     humaine
    -0.57
    ViewChild
    -0.57
    POSITIVE LOGITS
    OOTDTY
    0.46
    */)
    0.44
    inheritDoc
    0.44
     away
    0.43
    libft
    0.43
     f
    0.43
    illoin
    0.43
    orail
    0.42
    tsburgh
    0.42
    hdashline
    0.42
    Activations Density 0.002%

    No Known Activations