© 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. 1-RES-MATRYOSHKA-DC
    7. 1017
    Prev
    Next
    INDEX
    Explanations

    mentions of clinical risks or risk factors

    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
    possible
    -0.65
     possible
    -0.63
    Possible
    -0.62
     mulig
    -0.60
     possibles
    -0.60
     POSSIBLE
    -0.60
     möj
    -0.59
     Possible
    -0.58
    POSSIBLE
    -0.51
     možnosti
    -0.50
    POSITIVE LOGITS
     risk
    4.56
     Risk
    4.22
    risk
    4.09
    Risk
    4.03
     RISK
    3.86
    RISK
    3.50
     risks
    3.44
     Risks
    3.11
    risks
    3.02
     Risiko
    2.95
    Activations Density 0.334%

    No Known Activations