© 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. 2-RES-MATRYOSHKA-DC
    7. 2769
    Prev
    Next
    INDEX
    Explanations

    references to the manuscript or authors' contributions

    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
     فريبيس
    -0.56
     linkovi
    -0.54
     author
    -0.53
    NSNotification
    -0.51
     inflater
    -0.50
     ketahui
    -0.49
    action
    -0.48
     action
    -0.47
    author
    -0.47
     diketahui
    -0.47
    POSITIVE LOGITS
     manuscript
    3.36
     manuscripts
    2.48
     Manuscript
    2.44
    manus
    2.02
     Manuscripts
    1.88
     manuscrit
    1.84
    Manuscript
    1.82
     manus
    1.27
    Manus
    1.22
     Manus
    1.02
    Activations Density 0.004%

    No Known Activations