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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12724
    Prev
    Next
    INDEX
    Explanations

    elastic

    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
    rawDesc
    -0.56
     InputDecoration
    -0.56
    lüğ
    -0.56
    chability
    -0.54
    igshid
    -0.53
    //
    -0.52
     ocorreu
    -0.51
    ("")]
    
    -0.51
    worthiness
    -0.50
    */
    
    
    -0.48
    POSITIVE LOGITS
    ancien
    0.63
    BASELINE
    0.52
     commercial
    0.52
    commercial
    0.52
    recycled
    0.50
     Commercial
    0.49
     symbol
    0.49
     COMMERCIAL
    0.48
    defaultProps
    0.48
     commer
    0.47
    Activations Density 0.010%

    No Known Activations