© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13235
    Prev
    Next
    INDEX
    Explanations

    references to legal actions such as suing or lawsuits

    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
     commune
    -0.88
     Efq
    -0.84
     purpoſe
    -0.82
     perſon
    -0.75
     PeEnEo
    -0.71
     pleaſure
    -0.71
     houſe
    -0.70
     Inſ
    -0.70
     themſelves
    -0.69
     ſtre
    -0.69
    POSITIVE LOGITS
     sue
    3.08
    sue
    1.80
     sued
    1.77
     suing
    1.73
     SUE
    1.42
     Sue
    1.30
    Sue
    1.18
    errHandler
    0.66
     suoi
    0.61
    Rüyada
    0.59
    Activations Density 0.001%

    No Known Activations