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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16380
    Prev
    Next
    INDEX
    Explanations

    times of day

    np_max-act-logits · gemini-2.0-flash

    expressions of approximate time

    oai_token-act-pair · gemini-2.0-flash

    time approximations

    np_token-act-pair-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
    DoubleQuotes
    -0.90
    TagMode
    -0.64
    Clik
    -0.59
     CreateTagHelper
    -0.58
    RUnlock
    -0.53
    twimg
    -0.52
    rivial
    -0.52
    BoxShadow
    -0.51
    最快更新
    -0.50
    psack
    -0.49
    POSITIVE LOGITS
    chrift
    0.57
    rungsseite
    0.56
    ituary
    0.51
    ngdoc
    0.49
    stā
    0.48
    calyp
    0.48
    Legături
    0.47
     Tey
    0.47
     campfire
    0.46
     eruption
    0.45
    Activations Density 2.589%

    No Known Activations