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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14190
    Prev
    Next
    INDEX
    Explanations

    the word "prefix" and related terms in a programming context

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
    Prefix
    -0.65
    prefix
    -0.62
     prefix
    -0.60
    CheckedChanged
    -0.57
     đâu
    -0.57
    Ordinal
    -0.55
    SPATH
    -0.54
     Dostupné
    -0.52
     Erişim
    -0.51
    eterangan
    -0.50
    POSITIVE LOGITS
    <bos>
    1.50
     HttpNotFound
    0.63
    WriteTagHelper
    0.61
    IsContent
    0.59
    ^(@)
    0.57
     typelib
    0.57
    AndEndTag
    0.55
     تضيفلها
    0.55
    ंदीखरीदारी
    0.54
     InputDecoration
    0.54
    Activations Density 1.256%

    No Known Activations