© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5287
    Prev
    Next
    INDEX
    Explanations

    only

    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
     avoidance
    -0.56
    σια
    -0.55
     screws
    -0.54
     quantities
    -0.52
     misconception
    -0.52
     Terme
    -0.52
     stratum
    -0.52
     foods
    -0.52
     sandwiches
    -0.51
     misconceptions
    -0.50
    POSITIVE LOGITS
    antaranya
    0.78
    ValueStyle
    0.63
     للاسماء
    0.59
     sélectionnez
    0.57
    жели
    0.57
    tvguidetime
    0.56
     permitem
    0.56
    TintMode
    0.55
    商品説明
    0.53
    ftagPool
    0.52
    Activations Density 0.001%

    No Known Activations