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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14176
    Prev
    Next
    INDEX
    Explanations

    math expressions containing division

    oai_token-act-pair · gemini-2.0-flash

    Math equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     ModelExpression
    -0.70
    forChild
    -0.69
    énario
    -0.60
     Ips
    -0.58
    forRoot
    -0.53
    InputBorder
    -0.52
     Torr
    -0.52
    بوابة
    -0.51
    NSYLVANIA
    -0.51
    Portail
    -0.49
    POSITIVE LOGITS
     Six
    0.59
    6
    0.59
     six
    0.57
    六
    0.54
    TypedDataSet
    0.54
    Months
    0.52
     stabilis
    0.51
     months
    0.50
    enumi
    0.49
    XmlAccessorType
    0.49
    Activations Density 2.754%

    No Known Activations