© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5175
    Prev
    Next
    INDEX
    Explanations

    references to harm or damage caused by medical negligence

    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
     injury
    -1.95
     Injury
    -1.84
     injuries
    -1.69
    Injury
    -1.63
    injury
    -1.60
     Injuries
    -1.59
     INJ
    -1.45
    Injuries
    -1.39
     injured
    -1.27
    injured
    -1.15
    POSITIVE LOGITS
     damage
    2.30
     Damage
    2.05
    damage
    1.99
    Damage
    1.95
     DAMAGE
    1.94
     damages
    1.49
     Damages
    1.41
    DAMAGE
    1.34
     damaging
    1.30
     daño
    1.28
    Activations Density 0.021%

    No Known Activations