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. 22-CLT-HP
    4. 74289
    Prev
    Next
    INDEX
    Explanations

    in

    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
    ylase
    -0.55
     Infórmanos
    -0.54
     AspNetCore
    -0.49
     ald
    -0.48
     bounce
    -0.47
     bounces
    -0.47
    twimg
    -0.47
    oldo
    -0.47
    lamide
    -0.46
     initComponents
    -0.46
    POSITIVE LOGITS
    setVerticalGroup
    0.63
    قایناقلار
    0.62
    IndentedString
    0.59
    sendRedirect
    0.55
    matchCondition
    0.54
    
    0.53
     Zjednoc
    0.53
     hausse
    0.50
     Z
    0.49
    Z
    0.49
    Activations Density 0.008%

    No Known Activations