© 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. 1-CLT-HP
    7. 13503
    Prev
    Next
    INDEX
    Explanations

    RAE

    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
    RAE
    -0.83
    CustomAttributes
    -0.56
    TagHelper
    -0.56
    apunov
    -0.51
    ViewFeatures
    -0.49
    addContainerGap
    -0.48
    !*\
    -0.47
    meliharaan
    -0.47
    stagland
    -0.47
     للمعارف
    -0.46
    POSITIVE LOGITS
    DebuggerNonUser
    0.66
     Efq
    0.65
    hanger
    0.61
     Modeling
    0.61
    FieldBuilder
    0.57
     considér
    0.56
     Whis
    0.54
     Theoretical
    0.54
     modeling
    0.54
     $_"
    0.54
    Activations Density 0.018%

    No Known Activations