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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1539
    Prev
    Next
    INDEX
    Explanations

    recipes containing instructions for beer batter

    oai_token-act-pair · gemini-2.0-flash

    except

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
    tagHelperRunner
    -0.83
    Craft
    -0.81
     craft
    -0.79
     Craft
    -0.77
    sidemargin
    -0.77
    CRAFT
    -0.66
    BagLayout
    -0.63
    craft
    -0.63
     intptr
    -0.63
    webElementXpaths
    -0.61
    POSITIVE LOGITS
    HtmlAttribute
    0.57
    Salad
    0.54
    BASEPATH
    0.53
     Salad
    0.51
     Circus
    0.50
     Blumen
    0.49
    讐
    0.49
     Cocktail
    0.48
    principalTable
    0.48
    ναι
    0.47
    Activations Density 4.434%

    No Known Activations