© 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. 4-CLT-HP
    7. 4720
    Prev
    Next
    INDEX
    Explanations

    Foreign character

    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
     LoggerFactory
    -0.71
     disambiguazione
    -0.69
     IndexPath
    -0.69
     Normdatei
    -0.65
    RectangleBorder
    -0.63
    AutoresizingMask
    -0.60
    новниш
    -0.59
     ویکی‌پدیای
    -0.59
    ariConfig
    -0.56
    ěř
    -0.55
    POSITIVE LOGITS
     sanitaires
    0.60
    orite
    0.53
    adaran
    0.53
    findpost
    0.50
    ori
    0.48
     sauvages
    0.46
     énergé
    0.45
    出版年
    0.45
    mmation
    0.45
    مصادر
    0.45
    Activations Density 0.008%

    No Known Activations