© 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. 3-RES-MATRYOSHKA-DC
    7. 2028
    Prev
    Next
    INDEX
    Explanations

    discussion of workplace injuries, accidents, and negligence.

    oai_token-act-pair · gemini-2.0-flash
    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
    المناصب
    -0.59
     block
    -0.56
    ionario
    -0.55
     lack
    -0.53
    AxisAlignment
    -0.52
     obscure
    -0.51
    obscure
    -0.51
    itati
    -0.50
    nls
    -0.50
    Remover
    -0.50
    POSITIVE LOGITS
     Injury
    2.22
     injury
    2.20
    injury
    2.06
     injuries
    2.03
    Injury
    2.02
     damage
    1.96
     Injuries
    1.95
     injure
    1.88
     injured
    1.84
     Damage
    1.84
    Activations Density 0.760%

    No Known Activations