© 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. 2-RES-MATRYOSHKA-DC
    7. 5649
    Prev
    Next
    INDEX
    Explanations

    language indicating legal provisions, contractual terms, or statutory language

    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
    ISupport
    -0.64
    SPATH
    -0.57
    CastException
    -0.51
    RRect
    -0.49
    ViewStyle
    -0.48
     signs
    -0.48
     ProgressDialog
    -0.48
    äule
    -0.47
    TabStop
    -0.47
    :\/\/
    -0.46
    POSITIVE LOGITS
     loophole
    0.76
     ambiguity
    0.75
     wording
    0.73
     ambiguous
    0.72
     pleaſure
    0.69
     myſelf
    0.68
     phrasing
    0.68
     ambig
    0.67
     fevere
    0.67
     phrase
    0.66
    Activations Density 1.510%

    No Known Activations