© 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. 91026
    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
    젝
    -0.47
     Goldstein
    -0.47
     pesanan
    -0.44
    holt
    -0.44
    代わりに
    -0.44
    ypso
    -0.44
    шру
    -0.44
     Judd
    -0.43
     Bird
    -0.43
    osaurus
    -0.42
    POSITIVE LOGITS
    Билгалдахарш
    0.83
     BoxFit
    0.79
    Спољашње
    0.77
     ویکی‌پدی
    0.77
     Roskov
    0.71
     odkazy
    0.70
     فريبيس
    0.70
     InputDecoration
    0.67
    tvguidetime
    0.67
    Geplaatst
    0.66
    Activations Density 0.271%

    No Known Activations