© 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. 71394
    Prev
    Next
    INDEX
    Explanations

    downward movement

    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
     nahilalakip
    -0.72
    ImageContext
    -0.70
    msgTypes
    -0.69
    Források
    -0.66
     CEN
    -0.63
    SuccessListener
    -0.62
     Helium
    -0.60
    χεία
    -0.60
    JsonHelper
    -0.60
    日閲覧
    -0.60
    POSITIVE LOGITS
     Off
    0.41
     abajo
    0.41
     AssemblyCulture
    0.41
     indisponible
    0.40
     off
    0.39
    ientôt
    0.37
     autorytatywna
    0.37
     tärke
    0.36
     unders
    0.35
     @{
    0.35
    Activations Density 0.004%

    No Known Activations