© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1450
    Prev
    Next
    INDEX
    Explanations

    duplicated HTML form elements related to voting and choice selection

    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
    Negative Logits
    Class
    -1.30
     Classes
    -1.27
    IsContent
    -1.21
    CLASS
    -1.16
    Classes
    -1.13
     Theſe
    -1.13
    classes
    -1.12
    class
    -1.11
     CLASSES
    -1.08
     Class
    -1.06
    POSITIVE LOGITS
     the
    0.66
     most
    0.66
     
    0.66
     L
    0.64
     Sie
    0.64
     a
    0.62
     name
    0.61
     (
    0.59
     is
    0.59
     effect
    0.59
    Activations Density 0.131%

    No Known Activations