© 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. 3036
    Prev
    Next
    INDEX
    Explanations

    addressing the reader

    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
    richTextPanel
    -0.81
    parsedMessage
    -0.66
    elemField
    -0.66
    TagMode
    -0.62
     '\\;'
    -0.59
    ThroughAttribute
    -0.59
    dafx
    -0.58
    SourceChecksum
    -0.57
     propOrder
    -0.57
    gered
    -0.54
    POSITIVE LOGITS
     are
    0.84
     sleep
    0.80
     SLEEP
    0.56
     Sleep
    0.56
     compare
    0.56
     ARE
    0.55
     wait
    0.52
    are
    0.51
     schlafen
    0.50
    Sleep
    0.48
    Activations Density 0.005%

    No Known Activations