© 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. 7156
    Prev
    Next
    INDEX
    Explanations

    references to specific legal incidents or cases

    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
    JMenu
    -0.80
    rabh
    -0.69
     createState
    -0.66
     Carthage
    -0.64
    acebook
    -0.63
    lwjgl
    -0.63
    المناصب
    -0.62
     Puebla
    -0.60
    ">//
    -0.60
     Wildcard
    -0.60
    POSITIVE LOGITS
     incident
    3.22
     Incident
    2.86
    incident
    2.80
    Incident
    2.47
     incidents
    2.44
     Incidents
    2.19
     incidente
    1.80
     incidence
    1.54
     Incidence
    1.44
    incidence
    1.31
    Activations Density 0.010%

    No Known Activations