© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78118
    Prev
    Next
    INDEX
    Explanations

    Languages and Locations

    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
    Negative Logits
     Bulgarian
    -0.75
     Estonian
    -0.74
     Estonia
    -0.74
    expandindo
    -0.71
     Serbian
    -0.68
     مشين
    -0.67
     Bulgaria
    -0.66
     Bulgar
    -0.66
     gynhyrchwyd
    -0.66
     Moldova
    -0.65
    POSITIVE LOGITS
     paris
    0.50
    West
    0.47
     West
    0.46
     onAnimation
    0.43
     Франции
    0.43
    RectangleBorder
    0.42
    itier
    0.41
    paris
    0.40
     W
    0.39
    Germany
    0.39
    Activations Density 0.001%

    No Known Activations