© 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. 1012
    Prev
    Next
    INDEX
    Explanations

    references to instances of the word "due," typically indicating citation or attribution

    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
     source
    -0.88
     SOURCE
    -0.84
     Source
    -0.81
    source
    -0.77
    SOURCE
    -0.77
    WebVitals
    -0.74
     getSource
    -0.74
     источник
    -0.73
     Mean
    -0.73
     linkovi
    -0.73
    POSITIVE LOGITS
     due
    4.34
    due
    3.98
     Due
    3.81
    Due
    3.77
     DUE
    3.61
    DUE
    3.22
     debido
    2.94
     devido
    2.89
    Debido
    2.06
     owing
    2.03
    Activations Density 0.045%

    No Known Activations