© 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. 90858
    Prev
    Next
    INDEX
    Explanations

    physical spaces

    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
     civilian
    -0.44
     authenticity
    -0.44
     fhort
    -0.42
    GH
    -0.42
    trange
    -0.41
    Gizmos
    -0.40
    getBytes
    -0.40
     area
    -0.40
    resizingMask
    -0.39
    Xna
    -0.39
    POSITIVE LOGITS
     for
    1.02
    SuppressMessage
    0.66
    ngdoc
    0.65
    GTCX
    0.65
     réservé
    0.63
     recommandée
    0.60
    สำหรับ
    0.60
     untuk
    0.59
    berdayakan
    0.59
    ناصر
    0.57
    Activations Density 0.001%

    No Known Activations