© 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. 5-CLT-HP
    7. 2024
    Prev
    Next
    INDEX
    Explanations

    of

    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
    AsUp
    -0.74
    Билгалдахарш
    -0.70
    日閲覧
    -0.70
     BoxFit
    -0.69
     propOrder
    -0.67
     ویکی‌پدیای
    -0.64
    كويكب
    -0.64
    álás
    -0.61
    存于互联网档案馆
    -0.61
    الإنجليزية
    -0.60
    POSITIVE LOGITS
     volna
    0.48
     
    0.45
    esterno
    0.43
    NOPQRST
    0.42
    ={(
    0.39
     in
    0.39
    ebilir
    0.39
     around
    0.38
    rijfs
    0.38
     todėl
    0.38
    Activations Density 0.010%

    No Known Activations