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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94357
    Prev
    Next
    INDEX
    Explanations

    wars

    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
     الحره
    -0.69
    ⓧ
    -0.57
     Phaser
    -0.56
    Бележки
    -0.52
    slideshow
    -0.51
     للمعارف
    -0.49
    WriteLiteral
    -0.49
    olingo
    -0.48
     Thrust
    -0.48
    shire
    -0.48
    POSITIVE LOGITS
    CloseOperation
    0.71
    ImageContext
    0.60
     French
    0.59
     Italian
    0.58
     English
    0.58
     Swedish
    0.57
     italian
    0.55
     cherchés
    0.54
     Roman
    0.54
    English
    0.54
    Activations Density 0.000%

    No Known Activations