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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16241
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases including the word "the"

    oai_token-act-pair · gemini-2.0-flash

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
     autorytatywna
    -0.71
     []:
    -0.70
     Taktlose
    -0.63
     дописавши
    -0.57
    TintMode
    -0.55
     кӀ
    -0.54
    ьаж
    -0.53
     Normdatei
    -0.53
     GetEnumerator
    -0.53
    Initializable
    -0.52
    POSITIVE LOGITS
     Eſ
    0.61
     Theſe
    0.57
     becauſe
    0.57
     myſelf
    0.54
     douceur
    0.53
     Jefus
    0.53
     whoſe
    0.52
     reaſon
    0.52
     perſon
    0.52
     beſt
    0.51
    Activations Density 0.709%

    No Known Activations