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. 14224
    Prev
    Next
    INDEX
    Explanations

    words related to mathematical norms and also the word homogeneous

    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
     norm
    -0.78
    norm
    -0.68
     Norm
    -0.66
    Norm
    -0.65
     norms
    -0.60
    Nick
    -0.57
     nominate
    -0.56
     Nomination
    -0.55
     nick
    -0.54
     nominated
    -0.54
    POSITIVE LOGITS
    CloseOperation
    0.80
     utafitiHapana
    0.74
    ))^{
    0.69
    ."</
    0.65
    ⓧ
    0.65
    ()}}
    0.64
    XmlAccessType
    0.63
    ValueStyle
    0.63
    titleMargin
    0.62
    Bronnen
    0.61
    Activations Density 6.919%

    No Known Activations