© 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. 78079
    Prev
    Next
    INDEX
    Explanations

    rare or 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
    Negative Logits
    ंदीखरीदारी
    -0.77
    MergeFrom
    -0.62
     للمعارف
    -0.60
     pinulongan
    -0.56
    ganza
    -0.51
     preferências
    -0.50
     soste
    -0.49
    OrBuilder
    -0.49
     largeur
    -0.48
     ComVisible
    -0.48
    POSITIVE LOGITS
    wadi
    0.50
    XmlElement
    0.49
    ellschaft
    0.48
     chapter
    0.48
    ="@+
    0.46
    omst
    0.46
    pushFollow
    0.45
    nativeElement
    0.44
    enero
    0.44
     arşivlendi
    0.44
    Activations Density 0.000%

    No Known Activations