© 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. 97753
    Prev
    Next
    INDEX
    Explanations

    medical prefix "dys"

    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
     Monfieur
    -1.67
     Efq
    -1.64
     myſelf
    -1.55
     Majefty
    -1.44
     ainfi
    -1.38
     itſelf
    -1.38
     purpoſe
    -1.36
    клопе
    -1.34
     Shakspeare
    -1.34
     auffi
    -1.33
    POSITIVE LOGITS
     (
    0.70
     
    0.65
    ,
    0.62
     N
    0.61
     U
    0.59
     “
    0.59
     in
    0.57
     A
    0.56
     ‘
    0.56
     P
    0.56
    Activations Density 0.182%

    No Known Activations