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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11163
    Prev
    Next
    INDEX
    Explanations

    words related to medicines, hormones, and drugs that affect the nervous system

    oai_token-act-pair · gemini-2.0-flash

    terms related to sympathetic nervous system

    np_token-act-pair-logits · gpt-4o-mini

    sympathetic nervous system

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wpi
    -0.54
     bốn
    -0.50
     puh
    -0.48
    Gambas
    -0.44
    pul
    -0.44
    рации
    -0.43
    merate
    -0.43
    issaient
    -0.42
    DataColumn
    -0.42
    oneg
    -0.41
    POSITIVE LOGITS
     Symp
    0.77
     symp
    0.76
    symp
    0.75
     sympathetic
    0.73
    Nor
    0.71
    Locus
    0.71
     Nor
    0.70
    IUrlHelper
    0.69
    Symp
    0.68
     nor
    0.67
    Activations Density 3.339%

    No Known Activations