© 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. 45549
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     Opto
    -0.59
    DataAnnotations
    -0.58
     مشين
    -0.51
    resave
    -0.50
     linkovi
    -0.48
     '\\;'
    -0.47
     Lande
    -0.46
    printStackTrace
    -0.46
    entador
    -0.46
    EndInit
    -0.46
    POSITIVE LOGITS
    saraba
    0.70
    )•
    0.61
    ՚
    0.59
    >{@
    0.58
     wireType
    0.57
    外部リンク
    0.57
    FunctionFlags
    0.57
    Demografía
    0.57
    PyExc
    0.57
     "$@"
    0.57
    Activations Density 0.014%

    No Known Activations