© 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. 0-CLT-HP
    7. 45127
    Prev
    Next
    INDEX
    Explanations

    legal terms

    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
    men
    -0.63
    che
    -0.50
     possess
    -0.48
    umen
    -0.48
    kla
    -0.47
    ";
    -0.46
    >";
    -0.45
    ";
    -0.45
    </h5>
    -0.44
    hel
    -0.44
    POSITIVE LOGITS
    <bos>
    1.02
     onPostExecute
    0.91
     auffi
    0.88
     nakalista
    0.87
     itſelf
    0.86
     Monfieur
    0.85
     myſelf
    0.81
     GenerationType
    0.81
     LoggerFactory
    0.80
    httphttps
    0.79
    Activations Density 0.094%

    No Known Activations