© 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. 44082
    Prev
    Next
    INDEX
    Explanations

    welcome

    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
    <eos>
    -0.85
     
    -0.83
    ↵↵
    -0.77
    ↵
    -0.74
     (
    -0.73
     I
    -0.71
    .
    -0.71
     M
    -0.71
     or
    -0.68
     G
    -0.68
    POSITIVE LOGITS
     itſelf
    1.54
     myſelf
    1.52
     Houſe
    1.48
     Monfieur
    1.47
     doubtnut
    1.46
     ―――――
    1.46
     Anſ
    1.45
     Diſ
    1.45
     purpoſe
    1.44
     ſmall
    1.38
    Activations Density 2.925%

    No Known Activations