© 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. 3072
    Prev
    Next
    INDEX
    Explanations

    references to imminent danger or potential harm, specifically related to threats or menace

    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
    enderror
    -0.57
     commit
    -0.56
     createSprite
    -0.54
     Chbosky
    -0.52
    ⓧ
    -0.50
    setTag
    -0.50
    ?,?,
    -0.50
    лтемелер
    -0.49
    Jeb
    -0.49
    duit
    -0.49
    POSITIVE LOGITS
     threat
    3.28
    threat
    3.09
     Threat
    3.02
     threats
    2.97
    Threat
    2.94
     Threats
    2.86
    Threats
    2.56
     threatening
    2.47
     threatened
    2.41
     threaten
    2.39
    Activations Density 0.008%

    No Known Activations