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. 1729
    Prev
    Next
    INDEX
    Explanations

    the word "the" preceded by other words indicating time or the start of an event

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     introduced
    -0.67
    UrlResolution
    -0.59
     Introduced
    -0.58
    +:+
    -0.55
    AddHtmlAttribute
    -0.54
     дописавши
    -0.52
     introduce
    -0.52
     introduction
    -0.52
     Announcement
    -0.51
    introduced
    -0.51
    POSITIVE LOGITS
     Theſe
    0.68
     Efq
    0.60
    devServer
    0.57
    Einzelnachweise
    0.57
     juridique
    0.56
     againſt
    0.52
     regolare
    0.52
    Edits
    0.51
     greateſt
    0.51
     kaarangay
    0.50
    Activations Density 3.751%

    No Known Activations