© 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. 377
    Prev
    Next
    INDEX
    Explanations

    cat

    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
     ویکی‌پدی
    -0.77
     betweenstory
    -0.72
     Италијани
    -0.68
    MessageTagHelper
    -0.67
    osoba
    -0.66
    PyTuple
    -0.63
    :✨
    -0.61
     الرياضيه
    -0.61
    expandindo
    -0.60
    elemField
    -0.59
    POSITIVE LOGITS
     nahilalakip
    0.46
     sauter
    0.44
    市立
    0.41
     stedet
    0.40
     vorstellen
    0.40
     _("
    0.39
     scuro
    0.38
     ≠
    0.38
    /*:
    0.38
     wünschen
    0.37
    Activations Density 0.024%

    No Known Activations