© 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. 5-CLT-HP
    7. 91056
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act · 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
     a
    -0.64
    XmlAccessType
    -0.62
    AutoresizingMask
    -0.59
    abestanden
    -0.58
     déput
    -0.55
     assise
    -0.55
     émotion
    -0.55
    هات
    -0.54
     spesa
    -0.53
     démocr
    -0.52
    POSITIVE LOGITS
    LEncoder
    0.71
     normal
    0.54
     children
    0.52
    chitz
    0.50
    nestjs
    0.50
     scene
    0.49
    LookAnd
    0.49
     regular
    0.48
    paedia
    0.48
    Độ
    0.48
    Activations Density 0.003%

    No Known Activations