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. 5892
    Prev
    Next
    INDEX
    Explanations

    the word "about" or phrases that start with the word "about"

    oai_token-act-pair · gemini-2.0-flash

    words starting with "About"

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

    about

    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
    prox
    -0.55
    agens
    -0.55
     StatefulWidget
    -0.50
     ModelExpression
    -0.50
    gio
    -0.48
     Normdatei
    -0.47
    XmlAccessType
    -0.47
    ette
    -0.47
    org
    -0.46
    bie
    -0.46
    POSITIVE LOGITS
     disambiguazione
    0.59
    ThroughAttribute
    0.54
    postmedia
    0.53
    resave
    0.53
    اریخ
    0.53
    ograma
    0.53
     đông
    0.51
     Himo
    0.50
     BorderSide
    0.50
     initComponents
    0.50
    Activations Density 1.659%

    No Known Activations