© 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. 90982
    Prev
    Next
    INDEX
    Explanations

    featured

    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
    led
    -0.54
     to
    -0.47
    erialized
    -0.44
    to
    -0.44
     intéressante
    -0.42
     that
    -0.41
     Créez
    -0.41
    nan
    -0.41
     Medals
    -0.40
    είς
    -0.40
    POSITIVE LOGITS
    脚注の使い方
    0.81
    Personendaten
    0.78
    ddots
    0.64
     שוליים
    0.61
    IntoConstraints
    0.61
     mergeFrom
    0.60
    Sklici
    0.60
    ucson
    0.59
     Audiodateien
    0.57
    Atsauces
    0.57
    Activations Density 0.039%

    No Known Activations