© 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. 2-RES-MATRYOSHKA-DC
    7. 3180
    Prev
    Next
    INDEX
    Explanations

    words related to acts of violence or violent 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
     ExecuteAsync
    -0.69
    Datuak
    -0.60
     correctes
    -0.60
     remercier
    -0.54
    ască
    -0.51
    Swal
    -0.50
    Tetrach
    -0.50
     Nicolai
    -0.50
     commerciales
    -0.49
     Steff
    -0.49
    POSITIVE LOGITS
     violence
    3.33
     Violence
    3.08
    violence
    2.95
    Violence
    2.91
     violencia
    2.23
     violent
    2.02
     violência
    2.00
    violent
    1.98
     violences
    1.98
     violen
    1.96
    Activations Density 0.004%

    No Known Activations