© 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. 39780
    Prev
    Next
    INDEX
    Explanations

    structural/functional

    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
     of
    -0.60
     structural
    -0.60
     functional
    -0.56
    .
    -0.54
    s
    -0.54
    ing
    -0.53
    '
    -0.50
     ļ
    -0.49
     structurally
    -0.47
    Structural
    -0.47
    POSITIVE LOGITS
    ViewFeatures
    0.93
     فريبيس
    0.78
    styleType
    0.75
    tvguidetime
    0.72
    EndContext
    0.68
    DockStyle
    0.68
    extAlignment
    0.65
     disambiguazione
    0.65
    ConstraintMaker
    0.65
     ModelExpression
    0.63
    Activations Density 0.169%

    No Known Activations