© 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. 78185
    Prev
    Next
    INDEX
    Explanations

    numbers one and two

    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
     fourth
    -0.81
     quatro
    -0.76
     four
    -0.74
    EndGlobalSection
    -0.73
     cuatro
    -0.71
    cuatro
    -0.70
     Four
    -0.69
     Fourth
    -0.69
     FOURTH
    -0.69
    verwijspagina
    -0.68
    POSITIVE LOGITS
     seventeenth
    0.58
    2
    0.56
     Seventeenth
    0.54
     seventeen
    0.53
     Réponses
    0.52
     Seventeen
    0.50
    XXI
    0.49
     XVII
    0.49
    ೭
    0.48
    XVII
    0.48
    Activations Density 0.014%

    No Known Activations