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. 11128
    Prev
    Next
    INDEX
    Explanations

    words or characters used in programming or computer code

    oai_token-act-pair · gemini-2.0-flash

    equality and inequality operators

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

    comparison operators

    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
    parsedMessage
    -0.76
     estekak
    -0.74
    +#+#
    -0.71
     CreateTagHelper
    -0.68
     виправивши
    -0.67
     Ouverture
    -0.67
    Datuak
    -0.64
    makeConstraints
    -0.62
     ujednoznacz
    -0.61
    modelBuilder
    -0.61
    POSITIVE LOGITS
    ==
    0.99
     ==
    0.98
     !=
    0.81
    =="
    0.72
    !=
    0.71
    =='
    0.70
    ==="
    0.66
     =="
    0.66
     =='
    0.65
    !="
    0.64
    Activations Density 1.782%

    No Known Activations