© 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. 96269
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ikkert
    -0.63
     Attending
    -0.62
    PreExecute
    -0.62
     holotype
    -0.60
     attended
    -0.60
    NUMX
    -0.59
    ^(@)
    -0.59
    execSQL
    -0.58
     Arri
    -0.57
     attending
    -0.56
    POSITIVE LOGITS
     shed
    0.56
     store
    0.52
     apply
    0.50
     חיצוניים
    0.50
     "..\..\..\
    0.44
    tificate
    0.44
     للمعارف
    0.43
    ScopeManager
    0.43
     kasarigan
    0.43
     odkazy
    0.43
    Activations Density 0.004%

    No Known Activations