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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5946
    Prev
    Next
    INDEX
    Explanations

    mentions of dates written in the format "the late 19th century"

    oai_token-act-pair · gemini-2.0-flash

    words related to historical context

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

    9

    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
     ’
    -0.53
     
    -0.43
    ties
    -0.41
     Eigh
    -0.36
     fla
    -0.35
     '
    -0.35
    os
    -0.33
     Москвы
    -0.33
     forties
    -0.32
     jaren
    -0.32
    POSITIVE LOGITS
     ویکی‌پدیای
    1.00
    GEBURTS
    0.83
    EndInit
    0.79
    GeoNames
    0.76
     nahilalakip
    0.76
     '\\;'
    0.75
     الحره
    0.73
    énario
    0.73
    posedge
    0.70
     Италијани
    0.70
    Activations Density 0.265%

    No Known Activations