© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97432
    Prev
    Next
    INDEX
    Explanations

    convoy

    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
     للمعارف
    -0.68
    Дереккөздер
    -0.63
    Rujuakan
    -0.62
    Alike
    -0.62
    ScopeManager
    -0.59
    PerformLayout
    -0.57
    RenderAtEndOf
    -0.56
     חיצוניים
    -0.54
    typeparam
    -0.54
    fond
    -0.54
    POSITIVE LOGITS
    ionales
    0.46
     createContext
    0.41
    ără
    0.40
     Trails
    0.40
     camped
    0.39
     referenties
    0.37
    いだ
    0.37
    くだ
    0.37
     menuju
    0.36
    banners
    0.36
    Activations Density 0.001%

    No Known Activations