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. 14041
    Prev
    Next
    INDEX
    Explanations

    proper nouns in the entertainment industry, especially venues

    oai_token-act-pair · gemini-2.0-flash

    Events/venues

    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
    ViewFeatures
    -0.63
     '{@
    -0.60
    Kanpo
    -0.58
     Beine
    -0.57
    WEST
    -0.52
    Tazama
    -0.52
    abestanden
    -0.52
    ("$.
    -0.51
    ventional
    -0.50
     getBase
    -0.50
    POSITIVE LOGITS
    Portail
    0.51
     Bayou
    0.50
     太郎
    0.48
    brä
    0.48
     vectoriales
    0.48
     कीजिए
    0.46
    imir
    0.45
     Carrera
    0.45
    tilhar
    0.45
     conto
    0.45
    Activations Density 1.117%

    No Known Activations