© 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. 5995
    Prev
    Next
    INDEX
    Explanations

    references to financial support or funding sources

    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
    ing
    -0.56
     arşivlendi
    -0.56
    AddTagHelper
    -0.56
    ubin
    -0.53
    šanai
    -0.52
     bờ
    -0.52
     presumption
    -0.52
    eration
    -0.51
     householder
    -0.51
    Jawaban
    -0.50
    POSITIVE LOGITS
     funding
    3.02
     Funding
    2.89
    Funding
    2.88
    funding
    2.72
    FUNDING
    2.25
     funded
    2.23
    funded
    2.03
     Funded
    2.02
    Funded
    1.98
     funders
    1.95
    Activations Density 0.013%

    No Known Activations