© 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. 0-CLT-HP
    7. 90992
    Prev
    Next
    INDEX
    Explanations

    imba

    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
     Xerox
    -1.57
    imba
    -0.84
    KURZBESCHREIBUNG
    -0.71
     faſt
    -0.69
     myſelf
    -0.69
     Houſe
    -0.68
    resaid
    -0.67
     Reſ
    -0.66
     Hift
    -0.66
     itſelf
    -0.66
    POSITIVE LOGITS
    ed
    0.59
    es
    0.56
    LookAnd
    0.54
    ing
    0.50
     tiện
    0.50
    oredCriteria
    0.50
    rrggbb
    0.48
    MediaStore
    0.48
    Gambas
    0.48
    RenderAtEndOf
    0.48
    Activations Density 1.687%

    No Known Activations