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. 5832
    Prev
    Next
    INDEX
    Explanations

    mentions of the "blue slip" rule and words associated with it, within the context of the Senate.

    oai_token-act-pair · gemini-2.0-flash

    specific legal terminologies or concepts

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

    political procedures and nominations

    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
    出版年
    -0.66
    TagMode
    -0.61
    InitVars
    -0.59
    ⓧ
    -0.59
     AssemblyTitle
    -0.57
     lenker
    -0.56
    BufferException
    -0.56
    UnknownFields
    -0.54
    Cyfeiriadau
    -0.54
    Lähteet
    -0.54
    POSITIVE LOGITS
    ukah
    0.51
     coupable
    0.51
    lamp
    0.49
    markup
    0.48
    dote
    0.47
    Markup
    0.46
    tagHelper
    0.46
    GEBURTSDATUM
    0.43
    ingular
    0.43
    وصف
    0.43
    Activations Density 2.952%

    No Known Activations