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. 1622
    Prev
    Next
    INDEX
    Explanations

    the word "to" preceded by a verb or auxiliary verb

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    ANCE
    -0.54
    </caption>
    -0.54
     calendriers
    -0.52
     me
    -0.52
     Me
    -0.51
    หวัด
    -0.51
     transférez
    -0.50
     Réponses
    -0.50
     otomatig
    -0.50
    Diwedd
    -0.49
    POSITIVE LOGITS
    servable
    0.53
     accessibles
    0.48
     enfans
    0.47
     like
    0.47
    Torna
    0.47
     ineffective
    0.47
     etiam
    0.45
     juiz
    0.45
    akin
    0.45
     unworthy
    0.45
    Activations Density 4.424%

    No Known Activations