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. 11111
    Prev
    Next
    INDEX
    Explanations

    a variety of different words and phrases related to a few different topicsit triggers on a collection of words related to these topics:- data collection policies of websites- enabling browser cookies- words and numbers that are together, or that represent amounts- the word neolithic, and the

    oai_token-act-pair · gemini-2.0-flash

    tokens related to data collection

    np_token-act-pair-logits · gpt-4o-mini
    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
    ubscribe
    -0.54
    stopPropagation
    -0.53
    icor
    -0.51
     therefrom
    -0.50
     Ibid
    -0.50
    newState
    -0.49
     Idd
    -0.49
    <?>
    -0.48
    ïd
    -0.48
    ulties
    -0.48
    POSITIVE LOGITS
    वरी
    0.51
    -------------</
    0.51
    جوايز
    0.51
     their
    0.50
    their
    0.49
    Their
    0.49
     Leurs
    0.49
     okuyayım
    0.48
    Begriffsklä
    0.48
     Their
    0.47
    Activations Density 0.125%

    No Known Activations