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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16279
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash

    legal citations and discussions of legal cases

    oai_token-act-pair · gemini-2.0-flash

    Legal citations

    np_token-act-pair-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
    فایل‌لار
    -0.56
    expandindo
    -0.55
    Diweddarwch
    -0.53
    InputTagHelper
    -0.53
    évaluateur
    -0.51
    IUrlHelper
    -0.50
    rinth
    -0.49
    contentLoaded
    -0.49
     esterni
    -0.48
     <=",
    -0.47
    POSITIVE LOGITS
    BindView
    0.64
    CloseOperation
    0.63
    MENAFN
    0.56
    idazole
    0.54
    ########.
    0.52
    ̍
    0.49
     Closet
    0.49
    tableFuture
    0.49
    Artículo
    0.49
     Grüßen
    0.48
    Activations Density 2.923%

    No Known Activations