© 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. 1-RES-MATRYOSHKA-DC
    7. 570
    Prev
    Next
    INDEX
    Explanations

    references to legal failures or misconduct involving trial procedures or counsel

    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
    AndEndTag
    -0.73
     GenerationType
    -0.64
    yntaxException
    -0.63
    بوابة
    -0.60
    TagMode
    -0.60
     kors
    -0.59
     समीक्षक
    -0.57
     oignons
    -0.57
    Према
    -0.56
    RelativeTo
    -0.56
    POSITIVE LOGITS
     failed
    4.13
     failure
    3.98
     fail
    3.91
     Failure
    3.73
     fails
    3.69
     failing
    3.69
    failed
    3.55
     Failed
    3.45
     Fail
    3.42
    failure
    3.41
    Activations Density 0.104%

    No Known Activations