© 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. 6095
    Prev
    Next
    INDEX
    Explanations

    references to contractual breaches

    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
     estekak
    -0.89
    errHandler
    -0.88
    Hochspringen
    -0.84
    makeConstraints
    -0.84
    MessageTagHelper
    -0.84
     Andover
    -0.78
     Thon
    -0.76
    hank
    -0.74
     Parcelable
    -0.73
    |-
    -0.71
    POSITIVE LOGITS
    bre
    2.50
     Bre
    2.50
    Bre
    2.39
     BRE
    2.30
    BRE
    2.27
     breach
    2.08
     Breach
    1.88
     bre
    1.86
     breached
    1.77
     breaches
    1.72
    Activations Density 0.034%

    No Known Activations