© 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. 994
    Prev
    Next
    INDEX
    Explanations

    reducing negative impacts

    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
    illée
    -0.56
     Empfang
    -0.55
    ropoda
    -0.52
    readLine
    -0.50
    ypep
    -0.49
    delen
    -0.49
     brukes
    -0.49
    fitted
    -0.49
    örder
    -0.48
    ussis
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.69
    WebVitals
    0.61
    -------
    0.60
    ंदीखरीदारी
    0.59
    OGND
    0.58
     مشين
    0.56
    sizeCache
    0.53
    
    0.52
     building
    0.50
     room
    0.50
    Activations Density 0.005%

    No Known Activations