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. 6018
    Prev
    Next
    INDEX
    Explanations

    the word "the", especially when it begins a sentence or is followed by a noun

    oai_token-act-pair · gemini-2.0-flash

    terms related to soccer and match outcomes

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

    the

    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
    Datuak
    -0.59
    awaiter
    -0.54
     MainAxisSize
    -0.50
     تانيه
    -0.46
    complexContent
    -0.46
     manualmente
    -0.46
    XmlAccessType
    -0.45
     Wikimédia
    -0.45
    Parcelize
    -0.44
    /**
    -0.44
    POSITIVE LOGITS
     result
    0.63
    Czytaj
    0.60
     indisponible
    0.60
    migrationBuilder
    0.57
    IContainer
    0.57
     match
    0.56
    ConstraintMaker
    0.54
    genas
    0.54
     legs
    0.53
     disambiguazione
    0.52
    Activations Density 0.540%

    No Known Activations