© 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. 5948
    Prev
    Next
    INDEX
    Explanations

    references to medical shock events

    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
    樋
    -0.48
     Verd
    -0.47
     Pine
    -0.47
    SpringRunner
    -0.46
     Filosof
    -0.45
     Bahn
    -0.44
    xnn
    -0.44
    NOST
    -0.44
    Pine
    -0.43
    bahn
    -0.42
    POSITIVE LOGITS
     shock
    3.77
     Shock
    3.47
    shock
    3.41
    Shock
    3.33
     shocks
    2.92
     SHOCK
    2.88
     shocked
    2.34
    shocked
    2.20
    hock
    2.14
     shocking
    1.73
    Activations Density 0.017%

    No Known Activations