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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 429
    Prev
    Next
    INDEX
    Explanations

    Code/log data

    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
    AccessorTable
    -0.61
    WASH
    -0.57
    Geplaatst
    -0.57
    transQ
    -0.56
     Sver
    -0.56
    GEBURTSDATUM
    -0.56
    VersionUID
    -0.55
    PreExecute
    -0.54
    Personensuche
    -0.54
    wash
    -0.53
    POSITIVE LOGITS
    >`;
    0.49
    JavaScript
    0.48
    -@
    0.45
    stornos
    0.42
    قایناق‌لار
    0.42
     JsonConvert
    0.42
    ')):
    0.41
    twe
    0.40
    jection
    0.40
    PageModule
    0.39
    Activations Density 0.003%

    No Known Activations