© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72035
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · 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
     stand
    -0.54
    φό
    -0.49
     CreateTagHelper
    -0.49
     hoist
    -0.49
     ho
    -0.48
     frame
    -0.48
     station
    -0.48
    ESSOR
    -0.46
     illustrate
    -0.46
     race
    -0.46
    POSITIVE LOGITS
    Билгалдахарш
    0.66
     للمعارف
    0.65
    tahui
    0.57
     Seeder
    0.56
    matchCondition
    0.56
     okuyayım
    0.54
    SPATH
    0.54
    Datuak
    0.53
    Personensuche
    0.52
    GEBURTSDATUM
    0.51
    Activations Density 0.002%

    No Known Activations