© 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. 3196
    Prev
    Next
    INDEX
    Explanations

    references to harm or injury

    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
     damage
    -2.16
     Damage
    -2.00
    Damage
    -1.91
     DAMAGE
    -1.88
    damage
    -1.87
     damages
    -1.47
     Damages
    -1.42
    DAMAGE
    -1.38
     damaged
    -1.32
     Damaged
    -1.32
    POSITIVE LOGITS
     injury
    2.02
     Injury
    1.90
    Injury
    1.73
    injury
    1.71
     injuries
    1.70
     Injuries
    1.58
     INJ
    1.54
    Injuries
    1.38
     injured
    1.34
    injured
    1.21
    Activations Density 0.018%

    No Known Activations