© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5575
    Prev
    Next
    INDEX
    Explanations

    references to morally reprehensible acts or entities associated with evil and tragedy

    oai_token-act-pair · gpt-4.1-nano
    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
    Not in Any Lists

    No Comments

    Negative Logits
    balleur
    -0.62
     Lute
    -0.61
     breach
    -0.60
     Breach
    -0.59
    hnia
    -0.59
    jednoc
    -0.59
    Discre
    -0.59
    NameInMap
    -0.57
    Interrupt
    -0.57
    posedge
    -0.57
    POSITIVE LOGITS
     evil
    1.91
     Evil
    1.76
    evil
    1.73
    Evil
    1.73
     horror
    1.69
    horror
    1.55
     Horror
    1.52
    Horror
    1.52
     horrors
    1.34
     monster
    1.33
    Activations Density 0.334%

    No Known Activations