© 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. 3-RES-MATRYOSHKA-DC
    7. 1998
    Prev
    Next
    INDEX
    Explanations

    words containing the "re" prefix followed by other letters, especially when related to actions or states being repeated, or code

    oai_token-act-pair · gemini-2.0-flash
    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
    psack
    -0.65
    wpi
    -0.52
    ätzlich
    -0.50
    Marry
    -0.50
    Geplaatst
    -0.49
    koning
    -0.49
    pertino
    -0.48
    док
    -0.48
    oraus
    -0.48
     Betriebs
    -0.48
    POSITIVE LOGITS
     yeniden
    1.27
     again
    1.24
     ponownie
    1.24
     ulang
    1.23
     rebuilding
    1.22
     reconsideration
    1.22
     újra
    1.21
     rebuild
    1.20
     rewritten
    1.20
    重新
    1.19
    Activations Density 0.695%

    No Known Activations