© 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. 92487
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    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
     للاسماء
    -0.65
    Ethylbenzene
    -0.52
    ukų
    -0.49
     specific
    -0.49
     spécifiques
    -0.48
     ["
    -0.46
    gangenen
    -0.45
     unters
    -0.45
    ługo
    -0.44
    specific
    -0.44
    POSITIVE LOGITS
    djangoproject
    0.77
    AntiForgeryToken
    0.71
    mybatisplus
    0.66
    JNIEnv
    0.58
     виправивши
    0.57
    fastjson
    0.56
    EDEFAULT
    0.56
    Solución
    0.56
     downvoted
    0.56
    Aholisi
    0.56
    Activations Density 0.004%

    No Known Activations