© 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. 20-CLT-HP
    7. 74497
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · 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
    UnusedPrivate
    -0.43
    ньо
    -0.43
    Numerology
    -0.43
    Obrázky
    -0.42
    GenerationType
    -0.37
    oole
    -0.36
    最後
    -0.36
     fibroblasts
    -0.35
    SharedDtor
    -0.35
    はじめに
    -0.35
    POSITIVE LOGITS
    __":
    0.73
    apimachinery
    0.72
     laps
    0.71
    ьаж
    0.69
     meets
    0.66
     Division
    0.64
     Meets
    0.64
    __':
    0.62
    ulación
    0.60
    setVerticalGroup
    0.60
    Activations Density 0.006%

    No Known Activations