© 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. 90847
    Prev
    Next
    INDEX
    Explanations

    subscribe

    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
    脚注の使い方
    -0.78
    WithIOException
    -0.75
    IntoConstraints
    -0.74
     оригіналу
    -0.73
    Hauptartikel
    -0.71
    HomeAsUpEnabled
    -0.70
    Tembelea
    -0.64
     насељу
    -0.62
    terase
    -0.62
    writeFieldEnd
    -0.61
    POSITIVE LOGITS
     to
    0.65
     quiser
    0.45
    habhar
    0.44
     graça
    0.43
    To
    0.42
     Mercier
    0.41
    urization
    0.41
     gjen
    0.41
    varande
    0.41
     To
    0.41
    Activations Density 0.004%

    No Known Activations