© 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. 382
    Prev
    Next
    INDEX
    Explanations

    Gar

    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
    ConstraintMaker
    -0.57
     applied
    -0.54
     Gar
    -0.54
    )$/,
    -0.52
    ])[
    -0.51
    "])){
    -0.50
     Applied
    -0.48
    applied
    -0.48
    findOneAndUpdate
    -0.48
    
    -0.47
    POSITIVE LOGITS
     صوتيه
    0.75
    an
    0.69
    ans
    0.66
    Pautan
    0.65
     ComVisible
    0.65
    ments
    0.63
    mybatisplus
    0.61
     vallée
    0.60
     MenuView
    0.57
    StructEnd
    0.56
    Activations Density 0.033%

    No Known Activations