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. 14026
    Prev
    Next
    INDEX
    Explanations

    words related to vehicle engines, especially diesel and turbo engines

    oai_token-act-pair · gemini-2.0-flash

    Engine components

    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
    WebServlet
    -0.63
    NameInMap
    -0.63
    expandindo
    -0.62
    mockito
    -0.62
    OfYear
    -0.60
     Akismet
    -0.59
    reportWebVitals
    -0.58
    帖最后由
    -0.57
    VideoCapture
    -0.57
     Hase
    -0.56
    POSITIVE LOGITS
     charger
    0.59
     chargers
    0.53
    awtextra
    0.52
    super
    0.47
    Charger
    0.47
     Charge
    0.46
     charge
    0.46
    Charge
    0.45
    charger
    0.44
    CHARGE
    0.44
    Activations Density 0.629%

    No Known Activations