© 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. 72594
    Prev
    Next
    INDEX
    Explanations

    Code and technical documentation

    np_max-act-logits · 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
    Not in Any Lists

    No Comments

    Negative Logits
     faveur
    -0.61
     étoient
    -0.60
     avoient
    -0.59
     publiques
    -0.54
    maksud
    -0.54
     szív
    -0.54
     domestiques
    -0.54
     judicia
    -0.52
    withIdentifier
    -0.52
    aph
    -0.51
    POSITIVE LOGITS
     packed
    0.69
    PerformLayout
    0.64
     her
    0.59
    ربای
    0.58
    CppCodeGen
    0.58
    rawDesc
    0.57
    packed
    0.56
     jammed
    0.56
     h
    0.55
     ware
    0.55
    Activations Density 0.001%

    No Known Activations