Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74572
    Prev
    Next
    INDEX
    Explanations

    disease

    np_max-act-logits · 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
     Demand
    -2.89
    Demand
    -2.78
     demand
    -2.56
     DEMAND
    -2.47
    demand
    -2.42
     Demands
    -2.19
     demands
    -2.11
     demanded
    -1.97
     demanding
    -1.84
     demanda
    -1.84
    POSITIVE LOGITS
     Himo
    0.40
    IsInitialized
    0.39
    pageX
    0.37
    enapa
    0.36
    mbggenerated
    0.36
    lapsingToolbar
    0.36
    atchewan
    0.35
     Mascot
    0.35
     cuisson
    0.33
    WithEmail
    0.33
    Activations Density 0.081%

    No Known Activations