© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1219
    Prev
    Next
    INDEX
    Explanations

    references to recovery of damages or property following an incident 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
    DockStyle
    -0.66
    Tembelea
    -0.60
     failure
    -0.60
     Walkover
    -0.59
    adalajara
    -0.56
    Filmographie
    -0.56
    HostException
    -0.56
     appropriate
    -0.55
    oltà
    -0.55
    ürnberg
    -0.54
    POSITIVE LOGITS
     recovery
    2.98
     recover
    2.83
     Recovery
    2.81
    Recovery
    2.73
    recovery
    2.67
     recovered
    2.66
     recovers
    2.66
     RECOVERY
    2.58
     Recover
    2.56
     recovering
    2.47
    Activations Density 0.792%

    No Known Activations