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. 1612
    Prev
    Next
    INDEX
    Explanations

    legal and formally written texts, including citations and structured arguments (e.g., tort law, violation).

    oai_token-act-pair · gemini-2.0-flash

    Quotation marks

    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
    are
    -0.66
    have
    -0.63
    WebServlet
    -0.60
     références
    -0.59
    gets
    -0.59
    has
    -0.56
    things
    -0.56
    hares
    -0.56
    utilisons
    -0.55
    you
    -0.54
    POSITIVE LOGITS
    induced
    0.91
    based
    0.85
    driven
    0.80
    inspired
    0.79
    derived
    0.75
    funded
    0.74
    oriented
    0.73
    borne
    0.73
    like
    0.72
    related
    0.72
    Activations Density 22.892%

    No Known Activations