© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72549
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    таратура
    -0.67
    lewati
    -0.62
     fédé
    -0.57
     löytyy
    -0.56
     esboço
    -0.56
    IsContent
    -0.56
    berdayakan
    -0.56
     engraçadas
    -0.55
     avoient
    -0.54
    LEncoder
    -0.54
    POSITIVE LOGITS
     Pah
    0.70
     Rajput
    0.64
     Raj
    0.63
     Jain
    0.60
     Rajah
    0.59
     ayah
    0.58
     Thug
    0.57
     Sahib
    0.57
     mahar
    0.56
     Cey
    0.56
    Activations Density 0.000%

    No Known Activations