© 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. 2-RES-MATRYOSHKA-DC
    7. 4065
    Prev
    Next
    INDEX
    Explanations

    references to administrative or legal procedures and entities

    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
    KommentareTeilen
    -0.59
    tonsoft
    -0.57
    premier
    -0.52
    __(
    -0.49
     Marcell
    -0.49
    jsonString
    -0.49
    Premier
    -0.48
    pago
    -0.48
     (£
    -0.48
    IUrlHelper
    -0.47
    POSITIVE LOGITS
     administrative
    2.75
     Administrative
    2.70
    Administrative
    2.50
    administrative
    2.50
     administr
    1.94
     ADMINISTR
    1.89
    ADMINISTR
    1.76
     Administr
    1.67
     administrativa
    1.67
     administrativo
    1.62
    Activations Density 0.009%

    No Known Activations