© 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. 96275
    Prev
    Next
    INDEX
    Explanations

    related

    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
    šte
    -0.46
    جغرافيا
    -0.41
    load
    -0.40
    ટ
    -0.40
     milliers
    -0.39
    Double
    -0.39
     testigo
    -0.39
     Democrá
    -0.39
    getSimpleName
    -0.38
     uğ
    -0.38
    POSITIVE LOGITS
     intptr
    0.79
     Walkover
    0.69
    rungsseite
    0.68
     TextAlign
    0.67
     autorytatywna
    0.65
    transQ
    0.64
     gynhyrchwyd
    0.62
     dAtA
    0.61
    AnimationsModule
    0.61
    Архівовано
    0.60
    Activations Density 0.017%

    No Known Activations