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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1725
    Prev
    Next
    INDEX
    Explanations

    the phrase "such a" or "such an"

    oai_token-act-pair · gemini-2.0-flash

    such

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     the
    -0.61
    }}:
    -0.47
     Bhd
    -0.43
    hark
    -0.43
     cerevisiae
    -0.43
    cleros
    -0.42
     भार
    -0.41
    клопе
    -0.41
     GIPHY
    -0.41
    SizeF
    -0.41
    POSITIVE LOGITS
    paravant
    0.84
    Hauptartikel
    0.71
    AndEndTag
    0.71
    存于互联网档案馆
    0.70
     tartalomajánló
    0.70
    Tembelea
    0.69
    তথ্যসূত্র
    0.68
     CreateTagHelper
    0.66
     للمعارف
    0.65
    colhead
    0.65
    Activations Density 3.283%

    No Known Activations