© 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. 4-CLT-HP
    7. 4472
    Prev
    Next
    INDEX
    Explanations

    offers

    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
     Paglinawan
    -0.69
    LookAnd
    -0.60
    таратура
    -0.60
    thâu
    -0.57
    utebol
    -0.57
     समीक्षाओं
    -0.57
     Chopper
    -0.56
     unknownFields
    -0.56
    saraba
    -0.54
    iliares
    -0.54
    POSITIVE LOGITS
    bital
    0.50
    ândia
    0.47
    ViewChild
    0.47
    gmd
    0.45
    ptid
    0.44
     FetchType
    0.44
     Ost
    0.44
    getDoctrine
    0.43
    DropTable
    0.42
    SFD
    0.41
    Activations Density 0.001%

    No Known Activations