© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12174
    Prev
    Next
    INDEX
    Explanations

    atrop

    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
     Exile
    -0.79
     atrop
    -0.75
    setupUi
    -0.62
    NewLabel
    -0.57
    ActionCreators
    -0.57
    Архівовано
    -0.56
    __':
    
    -0.54
    autogui
    -0.54
    ליט
    -0.53
    CreateMap
    -0.52
    POSITIVE LOGITS
    Portale
    0.49
    __*/
    0.48
    protoimpl
    0.48
     Interv
    0.47
    );
    
    
    0.47
    iterrane
    0.45
     Wishing
    0.44
    ThroughAttribute
    0.44
     Eury
    0.44
     "")
    
    0.43
    Activations Density 0.013%

    No Known Activations