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. 74046
    Prev
    Next
    INDEX
    Explanations

    Articles/code/data

    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
     valued
    -0.65
     Values
    -0.64
     VAL
    -0.62
    values
    -0.60
     Valores
    -0.59
    valued
    -0.57
    Tē
    -0.56
    well
    -0.56
     values
    -0.56
     vuitton
    -0.55
    POSITIVE LOGITS
     asking
    0.48
     gyhoeddwyd
    0.47
    ForRow
    0.46
    InSection
    0.42
    XtraGrid
    0.42
    activated
    0.42
    ]]
    
    0.40
     ThemeData
    0.40
    endregion
    0.40
     Puis
    0.40
    Activations Density 0.000%

    No Known Activations