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. 5896
    Prev
    Next
    INDEX
    Explanations

    instances of "over the" or "the" followed by a time period

    oai_token-act-pair · gemini-2.0-flash

    temporal references in narratives

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

    the

    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
    AsUp
    -0.60
    !("{}",
    -0.50
    SharedDtor
    -0.50
     Efq
    -0.49
    berglass
    -0.46
    <?
    -0.46
     fread
    -0.45
    djangoproject
    -0.45
    ItemBackground
    -0.45
    aville
    -0.45
    POSITIVE LOGITS
     last
    0.69
     three
    0.61
     two
    0.59
    出版年
    0.59
     next
    0.58
    last
    0.55
     course
    0.52
     four
    0.52
    $',
    0.50
    明的
    0.49
    Activations Density 1.588%

    No Known Activations