© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15727
    Prev
    Next
    INDEX
    Explanations

    references to violent or aggressive behavior

    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
    rrggbb
    -0.73
    RenderAtEndOf
    -0.69
     sectional
    -0.66
    setScene
    -0.66
    /**
    -0.63
     métiers
    -0.61
    APIs
    -0.60
    ween
    -0.59
    batore
    -0.59
     Sche
    -0.59
    POSITIVE LOGITS
     interferon
    1.34
     violent
    1.12
    violent
    0.91
    Violent
    0.86
     Violent
    0.85
     violently
    0.76
     Monfieur
    0.76
     pleaſure
    0.73
     houſe
    0.71
     Efq
    0.71
    Activations Density 0.002%

    No Known Activations