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. 5829
    Prev
    Next
    INDEX
    Explanations

    content about lithium batteries

    oai_token-act-pair · gemini-2.0-flash

    terms related to battery technology

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

    Battery technology

    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
     autorytatywna
    -0.92
    DoubleQuotes
    -0.89
    FormTagHelper
    -0.85
    matchCondition
    -0.79
     ProtoMessage
    -0.77
     surla
    -0.75
     /\.(
    -0.74
    gonic
    -0.71
    tvguidetime
    -0.68
    Geplaatst
    -0.67
    POSITIVE LOGITS
     commercial
    0.46
     समीक्षक
    0.45
    isInitialized
    0.42
     ca
    0.41
    aimerais
    0.41
     working
    0.41
    Submitted
    0.41
    GF
    0.40
     advance
    0.39
     jäl
    0.39
    Activations Density 2.252%

    No Known Activations