© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93828
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цездатний
    -0.50
    ękuję
    -0.43
     voraus
    -0.43
     quân
    -0.42
    ivor
    -0.41
    eckel
    -0.41
     vor
    -0.41
    entliche
    -0.40
    Switching
    -0.39
     vi
    -0.39
    POSITIVE LOGITS
    tagHelperRunner
    0.95
     متعلقه
    0.86
     للاسماء
    0.86
    ValueStyle
    0.78
    modelBuilder
    0.70
    tanleria
    0.69
    Билгалдахарш
    0.67
    OrNil
    0.67
     дописавши
    0.66
     تانيه
    0.66
    Activations Density 0.000%

    No Known Activations