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. 6044
    Prev
    Next
    INDEX
    Explanations

    the word "He"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "He"

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

    he

    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
    mybatisplus
    -0.43
    stylesheet
    -0.42
    getDrawable
    -0.41
    ècie
    -0.40
     femelle
    -0.39
    ingtones
    -0.37
     braccia
    -0.36
    yafet
    -0.35
     knex
    -0.35
    UiThread
    -0.35
    POSITIVE LOGITS
    PyExc
    0.72
    RenderAtEndOf
    0.70
    AndEndTag
    0.67
     '\\;'
    0.63
    WithIOException
    0.63
    :✨
    0.62
    Jîn
    0.61
    PerformLayout
    0.60
    chafft
    0.59
    tagHelperRunner
    0.59
    Activations Density 0.318%

    No Known Activations