© 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. 71293
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and research

    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
     Italijani
    -0.59
     Référence
    -0.59
     ostavi
    -0.59
     AttributeSet
    -0.58
    InjectAttribute
    -0.54
     InputDecoration
    -0.52
     Holo
    -0.51
     SafeMath
    -0.51
    ettbewer
    -0.50
     Guel
    -0.50
    POSITIVE LOGITS
    centre
    0.45
    enumii
    0.45
     Gass
    0.45
     Sw
    0.45
    gezogen
    0.44
     saites
    0.43
    asks
    0.43
    Jeografia
    0.42
    Кры
    0.42
    Centre
    0.41
    Activations Density 0.000%

    No Known Activations