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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14169
    Prev
    Next
    INDEX
    Explanations

    the end of sentences followed by page numbers

    oai_token-act-pair · gemini-2.0-flash

    say 'page' or 'pages'

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
    slidesToShow
    -0.60
    twimg
    -0.60
     resourceCulture
    -0.57
     extracellular
    -0.55
     slate
    -0.52
    Biographie
    -0.52
     bony
    -0.52
     predictors
    -0.51
     databases
    -0.51
     WorldCat
    -0.51
    POSITIVE LOGITS
     CWE
    0.63
    tagHelper
    0.60
    fromnode
    0.55
    isNameExpr
    0.50
     <",
    0.50
     notizia
    0.47
     isNameExpr
    0.47
    FormTagHelper
    0.44
    Bronnen
    0.44
    >*/
    0.44
    Activations Density 1.104%

    No Known Activations