© 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. 78042
    Prev
    Next
    INDEX
    Explanations

    technical/instructional

    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
    TypedDataSet
    -0.71
    
    -0.62
    脚注の使い方
    -0.62
     kasarigan
    -0.61
    WriteBarrier
    -0.60
    AndEndTag
    -0.57
    sizeCache
    -0.57
    :+:
    -0.57
     EdgeInsets
    -0.56
     تضيفلها
    -0.56
    POSITIVE LOGITS
     staff
    0.55
     manuale
    0.54
     deportiva
    0.50
    vich
    0.49
    staff
    0.49
     toucher
    0.48
     Staff
    0.47
     velocities
    0.47
     Silber
    0.46
    glBegin
    0.46
    Activations Density 0.005%

    No Known Activations