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. 1-CLT-HP
    4. 12868
    Prev
    Next
    INDEX
    Explanations

    court documents

    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
    <bos>
    -0.61
     and
    -0.57
    ↵↵
    -0.52
    ↵
    -0.44
     of
    -0.43
     
    -0.41
     on
    -0.41
    and
    -0.40
     or
    -0.38
      
    -0.38
    POSITIVE LOGITS
    MeasureSpec
    0.69
     ProductService
    0.68
     nuages
    0.67
    uyler
    0.67
    AutoScaleMode
    0.66
     chrétien
    0.66
    amaño
    0.65
    BASEPATH
    0.64
    ſicht
    0.64
     ſans
    0.63
    Activations Density 0.098%

    No Known Activations