© 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. 0-CLT-HP
    7. 43234
    Prev
    Next
    INDEX
    Explanations

    transformation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     transformation
    -2.81
     transform
    -2.55
     Transformation
    -2.52
     transformed
    -2.45
    transformation
    -2.38
     transformations
    -2.34
    transform
    -2.31
     transforming
    -2.31
    Transformation
    -2.28
     transforms
    -2.11
    POSITIVE LOGITS
    ExtendWith
    0.65
    addPreferredGap
    0.57
     lige
    0.54
     рели
    0.54
    Jeho
    0.50
     elections
    0.49
     multin
    0.47
     flocc
    0.47
     cogni
    0.46
     religions
    0.46
    Activations Density 0.099%

    No Known Activations