© 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. 1-CLT-HP
    7. 12335
    Prev
    Next
    INDEX
    Explanations

    medical terminology

    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
    aline
    -1.48
    alin
    -1.02
    alina
    -0.83
    line
    -0.68
    alline
    -0.60
    GOTREF
    -0.58
     initComponents
    -0.52
     OMIT
    -0.50
    ELINE
    -0.45
     referenties
    -0.45
    POSITIVE LOGITS
    ثيق
    0.68
     الدولى
    0.67
     houſe
    0.63
    SCRIBE
    0.63
     iſt
    0.63
    parsedMessage
    0.62
    opheles
    0.61
    usercontent
    0.61
    aderie
    0.60
     NDL
    0.59
    Activations Density 0.013%

    No Known Activations