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. 0-CLT-HP
    4. 40857
    Prev
    Next
    INDEX
    Explanations

    paw

    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
    EndInit
    -0.79
    eline
    -0.69
     occasions
    -0.66
    ack
    -0.65
    出版年
    -0.65
    cies
    -0.63
    clave
    -0.59
    eq
    -0.56
     Occasionally
    -0.56
    ymal
    -0.55
    POSITIVE LOGITS
     للاسماء
    0.65
    LabelTagHelper
    0.60
    multer
    0.57
     AssemblyTitle
    0.55
    ("$.
    0.55
     GenerationType
    0.53
    NameInMap
    0.52
     مرئيه
    0.52
    sizeCache
    0.52
    ')}}">
    0.52
    Activations Density 1.637%

    No Known Activations