© 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. 0-RES-MATRYOSHKA-DC
    7. 10558
    Prev
    Next
    INDEX
    Explanations

    expressions related to potential or actual threats

    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
    Negative Logits
     threatened
    -1.25
     threaten
    -1.13
     threatening
    -1.11
     threatens
    -1.07
     Threatened
    -1.00
     menac
    -0.90
    threatening
    -0.85
    HandlerContext
    -0.73
     amenaz
    -0.72
    featureID
    -0.70
    POSITIVE LOGITS
     threat
    1.59
     Threat
    0.68
     danger
    0.57
    новништво
    0.57
    asymp
    0.55
    Према
    0.52
    infec
    0.51
     enemy
    0.48
    Empirical
    0.48
     ARR
    0.48
    Activations Density 0.002%

    No Known Activations