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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14049
    Prev
    Next
    INDEX
    Explanations

    arrays of decimal numbers ending in "]," or "])"

    oai_token-act-pair · gemini-2.0-flash

    digits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     ujednoznacz
    -0.68
    دانشنامهٔ
    -0.49
     ویکی‌پدیا
    -0.48
     ménages
    -0.46
     LCCN
    -0.45
    ënten
    -0.45
    filepath
    -0.44
     disambiguazione
    -0.43
     prés
    -0.43
    Становништво
    -0.42
    POSITIVE LOGITS
     externi
    0.63
    MigrationBuilder
    0.56
    complexContent
    0.53
     Mot
    0.53
    ]--;
    0.51
     lark
    0.50
    ]='\
    0.49
    itively
    0.49
     nont
    0.48
    JoinTable
    0.48
    Activations Density 1.691%

    No Known Activations