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. 11120
    Prev
    Next
    INDEX
    Explanations

    the preposition "in"

    oai_token-act-pair · gemini-2.0-flash

    tokens related to coding or programming structures

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

    in

    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
    󠁢
    -0.58
     avenir
    -0.56
    bited
    -0.52
    󠁧
    -0.51
    liances
    -0.51
    scryfall
    -0.50
    .*")]
    -0.49
     Vida
    -0.49
    Suivez
    -0.49
    ciale
    -0.49
    POSITIVE LOGITS
    IndentedString
    0.65
    ISupport
    0.57
    IonicModule
    0.54
    itemBuilder
    0.52
    ContentAsync
    0.49
    Jereo
    0.49
    protoimpl
    0.48
     ArrayAdapter
    0.48
    textTheme
    0.47
     Италијани
    0.47
    Activations Density 1.742%

    No Known Activations