© 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. 5-CLT-HP
    7. 913
    Prev
    Next
    INDEX
    Explanations

    death and violence

    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
    isNullOrEmpty
    -0.59
    Numerology
    -0.55
     duquel
    -0.54
    Географи
    -0.54
    ISupport
    -0.52
     trovo
    -0.52
     <<<<<<<<<<<<<<
    -0.51
    anceled
    -0.51
    Truly
    -0.50
    cepcion
    -0.50
    POSITIVE LOGITS
     
    0.60
     فريبيس
    0.54
     herself
    0.51
     estekak
    0.50
     nakalista
    0.50
     AssemblyCulture
    0.50
    oa̍t
    0.48
     kaarangay
    0.47
    herself
    0.47
    出版年
    0.46
    Activations Density 0.002%

    No Known Activations