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. 5903
    Prev
    Next
    INDEX
    Explanations

    the phrase "starting point" and related words.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "point"

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

    say "point"

    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
     AssemblyCulture
    -0.73
    Personendaten
    -0.70
    tvguidetime
    -0.54
    //
    -0.52
    ItemBackground
    -0.52
    Filmographie
    -0.51
    PreferredItem
    -0.51
    ToAction
    -0.50
     linkovi
    -0.49
    存于互联网档案馆
    -0.48
    POSITIVE LOGITS
     point
    2.69
     points
    2.52
    point
    2.44
     Point
    2.28
    Point
    2.25
    points
    2.25
     Points
    2.22
     POINT
    2.17
    POINT
    2.06
    Points
    2.03
    Activations Density 2.222%

    No Known Activations