© 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. 0-RES-MATRYOSHKA-DC
    7. 11745
    Prev
    Next
    INDEX
    Explanations

    references to extremist groups, specifically identifying mentions related to groups known for violence and terrorism

    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
    utsal
    -0.58
    üstü
    -0.56
    RUnlock
    -0.55
    -------------</
    -0.50
    annica
    -0.47
     Plin
    -0.46
    CompleteListener
    -0.46
     Voit
    -0.45
    currentColor
    -0.45
    ówka
    -0.45
    POSITIVE LOGITS
     ISIS
    2.36
     Hamas
    2.16
     Qaeda
    1.61
    ISIS
    1.59
     Isis
    1.33
     Hezbollah
    1.17
    Qaeda
    1.16
     Taliban
    1.02
     Boko
    0.96
    CodeAttribute
    0.91
    Activations Density 0.001%

    No Known Activations