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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2640
    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
    OGND
    -0.85
    GEBURTSDATUM
    -0.78
     AssemblyProduct
    -0.65
     بيها
    -0.64
     puppets
    -0.64
     tags
    -0.60
     options
    -0.60
    eaways
    -0.60
     franchises
    -0.59
     pyramids
    -0.59
    POSITIVE LOGITS
     esprits
    0.57
     eye
    0.57
     smile
    0.55
     feel
    0.53
     need
    0.52
     épaules
    0.52
    tainer
    0.51
     vœux
    0.50
     âmes
    0.50
     genoux
    0.50
    Activations Density 0.028%

    No Known Activations