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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11010
    Prev
    Next
    INDEX
    Explanations

    things on a food recipe ingredient list or a restaurant menu

    oai_token-act-pair · gemini-2.0-flash

    types of meat dishes

    np_token-act-pair-logits · gpt-4o-mini

    Types of meat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
     cherchés
    -0.63
    jws
    -0.55
    PROLOG
    -0.49
    BeginContext
    -0.48
     Bowser
    -0.48
    Бахар
    -0.47
    PerformLayout
    -0.47
    dealloc
    -0.46
    Bibliograf
    -0.46
    desa
    -0.46
    POSITIVE LOGITS
     lamb
    0.72
     chicken
    0.70
     pork
    0.67
     Chicken
    0.65
     meat
    0.65
     veal
    0.64
    beef
    0.64
     Beef
    0.63
     fish
    0.63
     Cordero
    0.63
    Activations Density 1.110%

    No Known Activations