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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1726
    Prev
    Next
    INDEX
    Explanations

    language related to capitalism, fascism, and class struggle

    oai_token-act-pair · gemini-2.0-flash

    Economy and politics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
    rungsseite
    -0.72
    Filmografie
    -0.62
     linkovi
    -0.60
     Paglinawan
    -0.59
    Cyfeiriadau
    -0.57
     مشين
    -0.54
    setupUi
    -0.54
    CloseOperation
    -0.53
    WebControls
    -0.52
    ptonshire
    -0.50
    POSITIVE LOGITS
    hetically
    0.58
    Merged
    0.57
    OfClass
    0.51
    OwnProperty
    0.51
    ்க்க
    0.48
     AssemblyCulture
    0.48
    SpringRunner
    0.47
    alaya
    0.47
    THISDAY
    0.47
    SourceChecksum
    0.47
    Activations Density 5.752%

    No Known Activations