© 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. 6-RES-MATRYOSHKA-DC
    7. 1151
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to accidents, injuries, and compensation

    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
    Nixon
    -0.59
     tartalomajánló
    -0.59
    tti
    -0.57
     block
    -0.56
    tate
    -0.56
    beg
    -0.56
    seid
    -0.56
    mpe
    -0.55
     mis
    -0.54
    zef
    -0.54
    POSITIVE LOGITS
     injury
    2.13
     Injury
    2.11
     injuries
    2.08
     Injuries
    2.08
    Injury
    2.00
    injury
    1.98
    Injuries
    1.89
     injured
    1.84
     INJ
    1.78
     Injured
    1.76
    Activations Density 0.222%

    No Known Activations