© 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. 1-CLT-HP
    7. 10960
    Prev
    Next
    INDEX
    Explanations

    general

    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
    StoryboardSegue
    -0.48
    yntaxException
    -0.44
    jacency
    -0.43
    gonic
    -0.40
     pilotes
    -0.39
    JsonInclude
    -0.39
    Terry
    -0.39
     flat
    -0.39
     gio
    -0.38
    úrese
    -0.38
    POSITIVE LOGITS
     dAtA
    0.69
     fermés
    0.64
     mourut
    0.60
    بوابة
    0.58
     dalamnya
    0.57
    مقاله
    0.57
     ویکی‌پدیای
    0.56
    Примітки
    0.56
     بيها
    0.54
     achievements
    0.53
    Activations Density 0.015%

    No Known Activations