© 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. 38765
    Prev
    Next
    INDEX
    Explanations

    diseases and medical procedures

    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
     purpoſe
    -1.46
     Shakspeare
    -1.36
     Monfieur
    -1.27
     myſelf
    -1.23
     Diſ
    -1.23
     itſelf
    -1.22
     raiſ
    -1.21
     ſtate
    -1.17
     ſeveral
    -1.17
     Anſ
    -1.16
    POSITIVE LOGITS
     
    0.71
     (
    0.65
     “
    0.65
     z
    0.65
     in
    0.63
     is
    0.61
     "
    0.60
     es
    0.60
     k
    0.59
    ,
    0.57
    Activations Density 0.115%

    No Known Activations