© 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. 92020
    Prev
    Next
    INDEX
    Explanations

    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
    ed
    -0.90
    i
    -0.87
    e
    -0.79
    ENCE
    -0.66
    iation
    -0.59
    ه
    -0.58
    a
    -0.57
    ition
    -0.57
    uration
    -0.56
    ured
    -0.54
    POSITIVE LOGITS
     continúas
    0.52
    capulco
    0.51
     Kamil
    0.50
     opal
    0.50
    principalColumn
    0.49
    otan
    0.49
    processable
    0.49
     COA
    0.49
     Bial
    0.49
     Occasional
    0.49
    Activations Density 0.132%

    No Known Activations