© 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. 44054
    Prev
    Next
    INDEX
    Explanations

    industrial

    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
    acial
    -0.73
    chard
    -0.56
     quarry
    -0.53
     haze
    -0.53
     Haz
    -0.50
    haz
    -0.44
    х
    -0.42
     Marina
    -0.42
    htar
    -0.42
    يله
    -0.41
    POSITIVE LOGITS
    ]='\
    0.79
     незавершена
    0.76
     snippetHide
    0.74
     Himo
    0.73
     itſelf
    0.73
    تقاوى
    0.73
     ModelExpression
    0.72
    polazione
    0.71
    tvguidetime
    0.70
    enumii
    0.66
    Activations Density 1.614%

    No Known Activations