© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10185
    Prev
    Next
    INDEX
    Explanations

    murder

    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
     murders
    -0.66
     Murders
    -0.62
     समीक्षक
    -0.58
    AndEndTag
    -0.57
    RectangleBorder
    -0.57
    PMailer
    -0.55
    ysacchar
    -0.55
     killings
    -0.54
     ✭✭
    -0.54
     majeurs
    -0.52
    POSITIVE LOGITS
    CreateMap
    0.50
    StoreMessageInfo
    0.50
     ejus
    0.48
     coö
    0.47
     autorytatywna
    0.47
    bitField
    0.47
    ableness
    0.47
    XmlEnum
    0.45
     depositphotos
    0.45
     незавершена
    0.45
    Activations Density 0.017%

    No Known Activations