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. 1617
    Prev
    Next
    INDEX
    Explanations

    the prepositions "in", "of", "for", and "on" and the determiner "the".

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    LabelTagHelper
    -0.53
    LLocation
    -0.53
    inafter
    -0.52
    তথ্যসূত্র
    -0.52
     BoxDecoration
    -0.51
     kasarigan
    -0.49
    mogen
    -0.48
    rizona
    -0.47
    лару
    -0.47
    CDCl
    -0.47
    POSITIVE LOGITS
     typelib
    0.53
    -
    0.53
     scher
    0.47
     AspNetCore
    0.44
    تقاوى
    0.44
     Désolé
    0.44
     circonst
    0.44
    _();
    0.43
    enumi
    0.43
    atimes
    0.42
    Activations Density 3.922%

    No Known Activations