© 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. 475
    Prev
    Next
    INDEX
    Explanations

    Military/government operations

    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
    <bos>
    -0.75
    клопе
    -0.45
     beginnetje
    -0.44
    ’
    -0.43
    ing
    -0.40
    ↵↵
    -0.39
    (
    -0.39
    versammlung
    -0.38
     destra
    -0.38
    espół
    -0.38
    POSITIVE LOGITS
    saraba
    0.74
     EnglishChoose
    0.73
     perfons
    0.72
     handleMessage
    0.71
     Majefty
    0.70
    tvguidetime
    0.70
     XCTest
    0.70
    TypedDataSet
    0.69
    améli
    0.68
     createState
    0.68
    Activations Density 0.028%

    No Known Activations