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. 11172
    Prev
    Next
    INDEX
    Explanations

    different forms of the verb "lay"

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'lay'

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

    lay

    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
    expandindo
    -0.95
     Paglinawan
    -0.74
     autorytatywna
    -0.63
     createState
    -0.62
     FetchType
    -0.60
    +#+#
    -0.60
    Демографія
    -0.58
     Exacts
    -0.57
     disambiguazione
    -0.57
    帖最后由
    -0.57
    POSITIVE LOGITS
    noinspection
    0.52
    jshint
    0.51
     PEND
    0.48
    thebibliography
    0.47
     resourceCulture
    0.46
    setupUi
    0.46
    ConverterFactory
    0.46
     Pend
    0.45
    endforeach
    0.45
    vignette
    0.45
    Activations Density 2.771%

    No Known Activations