© 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. 3112
    Prev
    Next
    INDEX
    Explanations

    mentions of primary or secondary clinical outcomes in study data

    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
    posedge
    -0.73
     survie
    -0.65
     Survive
    -0.64
    luß
    -0.63
     Oko
    -0.62
    ineno
    -0.60
    jgl
    -0.58
     vicinity
    -0.57
     dehors
    -0.57
    ardust
    -0.56
    POSITIVE LOGITS
     outcomes
    2.58
     Outcomes
    2.42
    outcomes
    2.25
    Outcomes
    2.20
     outcome
    2.19
     Outcome
    2.06
     OUTCOMES
    2.00
    outcome
    1.95
    Outcome
    1.76
    结局
    0.65
    Activations Density 0.014%

    No Known Activations