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. 5894
    Prev
    Next
    INDEX
    Explanations

    the string "av" in various contexts, particularly in filenames, code, and possibly as part of brand names or product names like "Avaya"

    oai_token-act-pair · gemini-2.0-flash

    terms starting with 'av'

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

    av

    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
    DockStyle
    -0.66
    setVerticalGroup
    -0.59
    GIVEREF
    -0.59
    Chham
    -0.57
    Vorlage
    -0.56
     foie
    -0.56
    meses
    -0.55
    OrBuilder
    -0.53
    spesies
    -0.52
     eslint
    -0.51
    POSITIVE LOGITS
     linkovi
    0.73
    ValueStyle
    0.63
     كومونز
    0.59
     שוליים
    0.55
    olz
    0.49
    amssymb
    0.46
     Sécurité
    0.45
     Савезне
    0.45
     combustível
    0.44
     Logement
    0.44
    Activations Density 0.186%

    No Known Activations