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. 20-CLT-HP
    4. 74119
    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
    XmlAccessType
    -0.41
     lightness
    -0.39
     enhanced
    -0.39
    detta
    -0.39
     rapid
    -0.39
     stunted
    -0.37
     expedited
    -0.37
     relaxed
    -0.37
     endogenous
    -0.36
    TAKT
    -0.36
    POSITIVE LOGITS
    ticides
    0.66
     inconn
    0.62
     cherchés
    0.59
     nôtre
    0.59
     inconnu
    0.59
     חיצוניים
    0.59
     Приступљено
    0.58
    IVEREF
    0.58
    requestCode
    0.58
     préféré
    0.58
    Activations Density 0.000%

    No Known Activations