© 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. 0-CLT-HP
    4. 45197
    Prev
    Next
    INDEX
    Explanations

    adjustment

    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
     Adjustment
    -1.00
     adjustment
    -0.91
    الحياه
    -0.88
    IContainer
    -0.85
    adjustment
    -0.85
     Anſ
    -0.84
    MigrationBuilder
    -0.82
     adaptation
    -0.82
     архивлан
    -0.81
     ProtoMessage
    -0.80
    POSITIVE LOGITS
     in
    0.40
     λό
    0.38
    ü
    0.35
    ,
    0.35
    ありがとうございます
    0.34
    .
    0.34
     lead
    0.34
    uss
    0.34
     raz
    0.34
    visející
    0.34
    Activations Density 0.048%

    No Known Activations