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. 74539
    Prev
    Next
    INDEX
    Explanations

    Medical/scientific texts

    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
     Skin
    -1.19
    Skin
    -1.02
     SKIN
    -1.01
     skin
    -0.99
    skin
    -0.93
     skins
    -0.91
    SKIN
    -0.85
    skinned
    -0.82
     Dermat
    -0.79
     skinned
    -0.77
    POSITIVE LOGITS
    Players
    0.53
     amet
    0.52
     EconPapers
    0.48
    saraba
    0.47
     pr
    0.45
    PageContext
    0.45
     Seeder
    0.44
    mappedBy
    0.44
     Inscrivez
    0.44
    EObject
    0.43
    Activations Density 0.241%

    No Known Activations