© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3456
    Prev
    Next
    INDEX
    Explanations

    words related to violent crime, especially rape, murder, kidnapping, and execution

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     adjuster
    -0.56
     methodName
    -0.49
     problemet
    -0.48
     Cadiz
    -0.46
    пло
    -0.46
     verhindern
    -0.46
     anom
    -0.45
     Himal
    -0.45
     Diwali
    -0.45
     affari
    -0.45
    POSITIVE LOGITS
     Torture
    0.86
    rape
    0.82
     rape
    0.80
     torture
    0.80
     kidnapping
    0.80
     kidnap
    0.79
     kidna
    0.79
     massacre
    0.77
     kidnapped
    0.77
    Autoritní
    0.77
    Activations Density 0.835%

    No Known Activations