© 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. 7352
    Prev
    Next
    INDEX
    Explanations

    references to legal pleas and plea agreements

    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
    boz
    -0.65
     Landes
    -0.56
    ⇑
    -0.53
     DER
    -0.52
    Distribuzione
    -0.50
    例句
    -0.50
    ceous
    -0.50
    Bibliography
    -0.49
    ietf
    -0.49
     jure
    -0.49
    POSITIVE LOGITS
     plea
    2.58
     Plea
    2.06
     pleas
    2.00
     pleaded
    1.52
     plead
    1.50
     pleads
    1.45
     pleading
    1.43
     Pleas
    1.20
     pled
    1.02
     PLE
    0.96
    Activations Density 0.006%

    No Known Activations