© 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. 1039
    Prev
    Next
    INDEX
    Explanations

    references to the severity or length of a judicial sentence

    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
    mybatisplus
    -0.69
    /**
    -0.67
    Odkazy
    -0.61
    ValueStyle
    -0.59
    خار
    -0.57
     kasarigan
    -0.56
    SharedCtor
    -0.55
    oltà
    -0.53
    goire
    -0.52
    φό
    -0.50
    POSITIVE LOGITS
     sentence
    4.19
     sentences
    3.53
     Sentence
    3.52
    sentence
    3.28
    Sentence
    2.98
     Sentences
    2.91
    sentences
    2.44
     sentenced
    2.33
     sentencing
    2.23
     SENT
    1.85
    Activations Density 0.249%

    No Known Activations