© 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. 1-CLT-HP
    7. 13083
    Prev
    Next
    INDEX
    Explanations

    Migration and displacement

    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
     AspNetCore
    -0.66
    <bos>
    -0.65
     emigrants
    -0.61
     from
    -0.60
     ModelExpression
    -0.59
     {?>
    -0.56
    structors
    -0.55
     cabinets
    -0.54
     Audiodateien
    -0.54
     skaters
    -0.52
    POSITIVE LOGITS
    StoryboardSegue
    0.67
     istore
    0.61
    bootstrapcdn
    0.59
    XMLSchema
    0.59
     kaynağından
    0.56
    ConstraintMaker
    0.56
    ContentAsync
    0.52
    addPreferredGap
    0.52
    GenerationType
    0.52
    niająca
    0.52
    Activations Density 0.049%

    No Known Activations