© 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. 7247
    Prev
    Next
    INDEX
    Explanations

    references to candidate articles or studies

    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
    Lähteet
    -0.65
    didSet
    -0.60
     ActionResult
    -0.59
    Хьажоргаш
    -0.59
    ToAction
    -0.58
     sequelize
    -0.56
     ویکی‌پدی
    -0.55
    CppCodeGen
    -0.55
    :][
    -0.55
    Brainz
    -0.55
    POSITIVE LOGITS
     candidate
    3.48
     candidates
    3.27
     Candidate
    3.19
     Candidates
    3.03
    candidate
    3.02
    Candidate
    3.00
    Candidates
    2.80
     CANDIDATE
    2.72
    candidates
    2.70
     candidats
    2.39
    Activations Density 0.018%

    No Known Activations