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. 5920
    Prev
    Next
    INDEX
    Explanations

    words related to research or the Internet

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb 'produce'

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

    producing

    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
     AssemblyTitle
    -0.73
     ControllerBase
    -0.66
    ✨:
    -0.59
     مرئيه
    -0.57
    antino
    -0.55
     continúas
    -0.54
    atko
    -0.52
    EDEFAULT
    -0.51
    ériques
    -0.50
     mCurrent
    -0.50
    POSITIVE LOGITS
     produce
    1.69
     produces
    1.65
     producing
    1.62
     yield
    1.58
     yields
    1.50
     yielding
    1.48
     yielded
    1.48
    yield
    1.48
     produced
    1.45
    produce
    1.42
    Activations Density 7.890%

    No Known Activations