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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16218
    Prev
    Next
    INDEX
    Explanations

    words related to academic research

    oai_token-act-pair · gemini-2.0-flash

    scientific publications

    np_token-act-pair-logits · gemini-2.0-flash

    Research studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
     saites
    -0.59
    IsContent
    -0.56
     disambiguazione
    -0.53
    XmlEnum
    -0.53
    delwed
    -0.52
    Reparto
    -0.52
     ligiloj
    -0.51
    bric
    -0.50
    ApiOperation
    -0.49
     hậu
    -0.48
    POSITIVE LOGITS
     nahilalakip
    0.62
     ContentValues
    0.60
    protoimpl
    0.58
    DoubleQuotes
    0.57
    windowFixed
    0.56
    intios
    0.54
    ArrowToggle
    0.53
     femininas
    0.52
    webElement
    0.52
    orianCalendar
    0.49
    Activations Density 2.005%

    No Known Activations