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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97707
    Prev
    Next
    INDEX
    Explanations

    Rug

    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
    zbęd
    -0.60
    ']));
    -0.58
     بيها
    -0.56
     Rug
    -0.56
    '));
    -0.56
    ACF
    -0.55
     invokingState
    -0.54
    ]){
    -0.54
     Гра
    -0.53
     AspNetCore
    -0.53
    POSITIVE LOGITS
    Pautan
    0.62
     Egypt
    0.53
    SuppressMessage
    0.53
     transfieras
    0.51
    Abitanti
    0.51
    enação
    0.50
    haupt
    0.49
     Egyptian
    0.48
     plats
    0.48
    eburger
    0.48
    Activations Density 0.193%

    No Known Activations