© 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. 560
    Prev
    Next
    INDEX
    Explanations

    references to legal principles or constitutional protections

    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
    RetentionPolicy
    -0.89
    RemoveField
    -0.61
    RTLI
    -0.58
    nict
    -0.57
    itures
    -0.56
     مشين
    -0.56
    Risultati
    -0.56
     fragmentary
    -0.55
     mortgagee
    -0.54
     ControllerBase
    -0.54
    POSITIVE LOGITS
     equal
    4.16
     Equal
    3.80
    equal
    3.77
    Equal
    3.59
     EQUAL
    3.39
    EQUAL
    2.83
     equality
    2.66
     égal
    2.61
     equ
    2.48
     equals
    2.45
    Activations Density 0.556%

    No Known Activations