© 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. 4-CLT-HP
    7. 1064
    Prev
    Next
    INDEX
    Explanations

    require

    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
    onActivityResult
    -0.46
    yfik
    -0.46
    --)
    -0.46
     or
    -0.45
    zem
    -0.43
    实际
    -0.42
     at
    -0.41
     lại
    -0.41
     earthquake
    -0.41
    AspNet
    -0.41
    POSITIVE LOGITS
     للاسماء
    0.89
     مشين
    0.88
    httphttps
    0.78
     الحره
    0.77
     nahilalakip
    0.76
     transfieras
    0.72
     AssemblyTitle
    0.72
    webElementXpaths
    0.72
    JNIEnv
    0.69
     désolés
    0.69
    Activations Density 0.009%

    No Known Activations