Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14297
    Prev
    Next
    INDEX
    Explanations

    the word "where" within mathematical notation

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
     where
    -2.41
    where
    -2.13
    Where
    -1.75
     Where
    -1.70
     WHERE
    -1.68
     donde
    -1.57
    WHERE
    -1.49
     où
    -1.48
     где
    -1.39
    donde
    -1.30
    POSITIVE LOGITS
    findpost
    0.65
    $")
    0.65
     TestBed
    0.64
    BorderFactory
    0.61
    ôts
    0.60
    oa̍t
    0.60
    }")
    
    0.59
    argout
    0.59
    BASEPATH
    0.59
    rowave
    0.57
    Activations Density 1.105%

    No Known Activations