© 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. 1-RES-MATRYOSHKA-DC
    7. 1555
    Prev
    Next
    INDEX
    Explanations

    references to the persistence or leftover elements of events or objects

    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
    Negative Logits
    навли
    -0.76
     bezeichneter
    -0.70
    entile
    -0.67
     LoggerFactory
    -0.66
    basicConfig
    -0.63
     keeping
    -0.63
     Keeping
    -0.60
     linkovi
    -0.59
    keep
    -0.58
     Nell
    -0.58
    POSITIVE LOGITS
     remain
    3.44
     remains
    3.36
    remain
    3.14
     remained
    3.09
    remains
    3.09
     Remains
    2.92
     Remain
    2.86
     remaining
    2.77
    Remain
    2.61
     Remaining
    2.50
    Activations Density 0.425%

    No Known Activations