Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16373
    Prev
    Next
    INDEX
    Explanations

    Diverse content

    np_max-act-logits · gemini-2.0-flash

    terms related to business accounting and taxation

    oai_token-act-pair · gemini-2.0-flash

    code or programming language

    np_token-act-pair-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
     nahilalakip
    -0.63
    出版年
    -0.61
     AssemblyProduct
    -0.59
     pprint
    -0.54
    scriber
    -0.53
    abank
    -0.53
    bbler
    -0.52
    — 
    -0.52
    etter
    -0.51
    gner
    -0.50
    POSITIVE LOGITS
    findpost
    0.72
     beginnetje
    0.57
    RectangleBorder
    0.54
    InitVars
    0.54
     AspNetCore
    0.54
    complexContent
    0.50
     '\\;'
    0.50
     resourceCulture
    0.49
     disambiguazione
    0.49
    +#+#
    0.48
    Activations Density 2.237%

    No Known Activations