© 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. 20-CLT-HP
    7. 74996
    Prev
    Next
    INDEX
    Explanations

    Accidents/negative events

    np_max-act-logits · 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
     Walks
    -0.97
     esercit
    -0.93
     câte
    -0.93
     tours
    -0.90
    tours
    -0.87
     Visits
    -0.84
     ripet
    -0.84
     parades
    -0.84
     pngtree
    -0.83
     hunts
    -0.83
    POSITIVE LOGITS
    netinet
    0.34
     statt
    0.30
     
    0.29
     ModelExpression
    0.29
    原始内容存档于
    0.28
    <eos>
    0.28
     campi
    0.28
    неопр
    0.27
    arXiv
    0.26
     portait
    0.26
    Activations Density 0.005%

    No Known Activations