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. 5875
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "you will"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "you" and related terms

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

    Talking to "you"

    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
     Wikimedijinoj
    -0.72
    fortawesome
    -0.64
     الدولى
    -0.61
    Autoritní
    -0.57
    iesa
    -0.56
    шай
    -0.56
    jupiter
    -0.55
     mocht
    -0.54
    ration
    -0.54
    madre
    -0.53
    POSITIVE LOGITS
    CppMethod
    0.48
    prefixer
    0.47
    windowFixed
    0.46
    tront
    0.45
    druid
    0.43
    INGREDIENTES
    0.43
    enumi
    0.42
    //
    0.41
    odeon
    0.41
     transfieras
    0.41
    Activations Density 0.902%

    No Known Activations