Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11050
    Prev
    Next
    INDEX
    Explanations

    descriptions of misconduct and bad behavior

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "physical"

    np_token-act-pair-logits · gpt-4o-mini

    physical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.79
    MigrationBuilder
    -0.69
     createState
    -0.60
    новништво
    -0.60
     umane
    -0.59
    ніципалі
    -0.56
    getResultList
    -0.54
    
    -0.54
     StatelessWidget
    -0.54
    initComponents
    -0.54
    POSITIVE LOGITS
     physical
    0.96
     Physical
    0.91
    Physical
    0.83
    physical
    0.81
     PHYSICAL
    0.81
     physically
    0.79
    PHYSICAL
    0.75
     fysis
    0.70
     fisik
    0.68
    phys
    0.66
    Activations Density 3.085%

    No Known Activations