© 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. 5-CLT-HP
    7. 91246
    Prev
    Next
    INDEX
    Explanations

    code errors

    np_max-act · 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
     nakalista
    -0.82
     fubject
    -0.67
    RenderAtEndOf
    -0.66
    ֹא
    -0.63
    OptionsMenu
    -0.60
    хьтан
    -0.60
     AttributeSet
    -0.59
     perfons
    -0.59
    Demografia
    -0.58
     manifestly
    -0.58
    POSITIVE LOGITS
    printStackTrace
    0.50
    Viitteet
    0.47
    ArgsConstructor
    0.46
    openzeppelin
    0.46
     noqa
    0.43
    ‚¬
    0.42
    jsonwebtoken
    0.42
    SqlDataReader
    0.41
    setof
    0.41
    @[+][
    0.40
    Activations Density 0.028%

    No Known Activations