Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74496
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · 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
    ArrowToggle
    -0.77
     مشين
    -0.60
     الحره
    -0.57
     חיצוניים
    -0.56
    पया
    -0.54
    Referanser
    -0.51
    tagext
    -0.50
    Примітки
    -0.50
     للمعارف
    -0.50
     lenker
    -0.49
    POSITIVE LOGITS
     mosso
    0.62
     avoient
    0.61
     acrylique
    0.58
     vettor
    0.57
     étoit
    0.57
     thermique
    0.56
     commerciali
    0.56
     giapp
    0.55
     duquel
    0.54
     mérit
    0.54
    Activations Density 0.003%

    No Known Activations