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. 5844
    Prev
    Next
    INDEX
    Explanations

    phrases containing the words "way", "time", or "other".

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "around"

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

    around round

    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
    -0.70
    AccessorTable
    -0.69
     continúas
    -0.65
    upuncture
    -0.63
    })*/
    -0.62
     समीक्षक
    -0.61
     通販
    -0.60
     EconPapers
    -0.60
     BoxFit
    -0.59
    はじめに
    -0.59
    POSITIVE LOGITS
     around
    2.91
     round
    2.55
    around
    2.52
     Around
    2.50
    Around
    2.42
    round
    2.30
     AROUND
    2.30
    AROUND
    2.03
     Round
    2.03
    Round
    2.02
    Activations Density 1.274%

    No Known Activations