© 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. 92143
    Prev
    Next
    INDEX
    Explanations

    power

    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
     BoxDecoration
    -0.67
     Power
    -0.50
    PostMapping
    -0.50
     power
    -0.49
    go
    -0.48
    migrationBuilder
    -0.48
    HasAnnotation
    -0.47
     iArr
    -0.47
    rawDesc
    -0.47
    ilina
    -0.44
    POSITIVE LOGITS
    +#+#
    0.83
     ModelExpression
    0.73
     rechange
    0.68
     estimés
    0.66
    TypedDataSet
    0.63
    expandindo
    0.60
    erie
    0.58
    multicolumn
    0.57
     Marra
    0.57
    Портали
    0.55
    Activations Density 0.029%

    No Known Activations