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. 14092
    Prev
    Next
    INDEX
    Explanations

    language related to academic proposals and requests

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    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
    Datuak
    -0.89
    躇
    -0.77
    исленность
    -0.71
     GenerationType
    -0.66
    DockStyle
    -0.65
    execSQL
    -0.64
    multer
    -0.60
     propOrder
    -0.60
    FlatList
    -0.60
    cipar
    -0.60
    POSITIVE LOGITS
    enumi
    0.59
    Портал
    0.47
     center
    0.45
     committees
    0.43
    Schule
    0.43
     teaching
    0.41
     kaarangay
    0.40
     imagine
    0.40
     value
    0.40
    INIT
    0.40
    Activations Density 7.462%

    No Known Activations