© 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. 92071
    Prev
    Next
    INDEX
    Explanations

    medicine

    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
     medication
    -1.23
     Medication
    -1.04
    Medication
    -0.99
     medications
    -0.98
     Medications
    -0.85
    medication
    -0.85
     coffee
    -0.79
     meds
    -0.75
     drugs
    -0.71
     médicaments
    -0.68
    POSITIVE LOGITS
    bibinfo
    0.60
    einem
    0.53
    STRENGTH
    0.53
    ))))))))
    0.53
    />";
    0.50
    UnknownFieldSet
    0.48
     raiſ
    0.48
    principalTable
    0.48
    bibfield
    0.47
     itſelf
    0.47
    Activations Density 0.508%

    No Known Activations