© 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. 324
    Prev
    Next
    INDEX
    Explanations

    references to injury and tissue damage

    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
    Tikang
    -0.60
    False
    -0.59
    /*
    -0.58
     False
    -0.57
    verifyException
    -0.56
    relativeTime
    -0.54
    المناصب
    -0.52
    期刊论文
    -0.52
    false
    -0.51
    FALSE
    -0.51
    POSITIVE LOGITS
     injury
    3.23
     damage
    3.17
     Injury
    3.02
     Damage
    2.97
     injuries
    2.92
    injury
    2.86
    Injury
    2.80
    damage
    2.78
     DAMAGE
    2.73
    Damage
    2.70
    Activations Density 1.361%

    No Known Activations