© 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. 5-CLT-HP
    7. 5185
    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
    ArgumentParser
    -0.69
     EconPapers
    -0.62
     المعيارى
    -0.59
    CodedInputStream
    -0.59
    脚注の使い方
    -0.59
     murale
    -0.58
    sizeCache
    -0.58
     caseros
    -0.58
     NavController
    -0.57
     reç
    -0.56
    POSITIVE LOGITS
     mergeFrom
    0.47
     Program
    0.44
     @[
    0.44
     learn
    0.39
     programu
    0.39
     teach
    0.39
    NullException
    0.38
     Learn
    0.38
     Programs
    0.38
     Reverso
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.