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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16321
    Prev
    Next
    INDEX
    Explanations

    words related to GPS navigation and car accessories

    oai_token-act-pair · gemini-2.0-flash

    GPS and navigation

    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
     kasarigan
    -0.62
    DoubleQuotes
    -0.57
    دانشنامهٔ
    -0.54
    )++;
    -0.54
     EconPapers
    -0.52
     Ceinture
    -0.51
     Shakspeare
    -0.51
    jooq
    -0.50
     Shaksp
    -0.48
     natale
    -0.48
    POSITIVE LOGITS
    routeProvider
    0.57
    URLException
    0.54
     Satellite
    0.54
     emergencia
    0.52
    edra
    0.52
     navigation
    0.49
     satellite
    0.49
    dieran
    0.49
    ietf
    0.48
    Distribuzione
    0.48
    Activations Density 1.021%

    No Known Activations