© 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. 4268
    Prev
    Next
    INDEX
    Explanations

    references to specific Amendments of the U.S. Constitution

    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
    StoryboardSegue
    -0.69
     duquel
    -0.61
    fjspx
    -0.61
    WEBPACK
    -0.59
    daß
    -0.59
    ('*',
    -0.59
     PyTuple
    -0.57
    IsContent
    -0.56
     ویکی‌پدیا
    -0.56
    iez
    -0.55
    POSITIVE LOGITS
     Amendment
    3.20
    Amendment
    2.55
     amendment
    2.52
     AMEND
    2.25
     Amendments
    2.13
     amendments
    1.83
    amend
    1.78
     Amend
    1.56
    Amend
    1.51
     amend
    1.32
    Activations Density 0.006%

    No Known Activations