© 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. 4-CLT-HP
    7. 4308
    Prev
    Next
    INDEX
    Explanations

    medical studies

    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
    Personendaten
    -0.80
    WithIOException
    -0.73
    oredCriteria
    -0.70
     <=",
    -0.69
    SourceChecksum
    -0.69
    featureID
    -0.67
    WebVitals
    -0.66
    InitVars
    -0.66
    webElementXpaths
    -0.65
    AndEndTag
    -0.64
    POSITIVE LOGITS
     arise
    0.63
     arrive
    0.60
     belong
    0.59
     emerge
    0.59
     hail
    0.56
     fail
    0.55
    ėjimas
    0.55
     arose
    0.54
     circulate
    0.53
     reappear
    0.53
    Activations Density 0.006%

    No Known Activations