© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1798
    Prev
    Next
    INDEX
    Explanations

    Formal 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
    queryInterface
    -0.76
    %");
    -0.74
    
    -0.71
    endphp
    -0.70
    UnitTesting
    -0.70
    UserScript
    -0.69
     \%)
    -0.68
    argout
    -0.66
    Parabéns
    -0.66
    KEYCODE
    -0.65
    POSITIVE LOGITS
    hood
    0.54
     tale
    0.45
    More
    0.45
     tease
    0.44
    yd
    0.44
    german
    0.43
    warmup
    0.43
     Fuchs
    0.43
    ad
    0.42
    ICY
    0.42
    Activations Density 0.052%

    No Known Activations