© 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. 7442
    Prev
    Next
    INDEX
    Explanations

    references to specific types of scientific or technical patents or publications

    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
    WebElementEntity
    -0.69
     Ti
    -0.56
     tibia
    -0.53
    ்க
    -0.50
    PLAC
    -0.49
    fdb
    -0.48
     Needham
    -0.48
    scarpe
    -0.47
    succeeded
    -0.47
    atimes
    -0.47
    POSITIVE LOGITS
    tic
    3.14
    tics
    1.59
    tică
    1.23
    ticum
    1.20
    ticity
    1.17
    TIC
    1.16
    tiche
    1.08
    tica
    1.07
    tically
    1.05
    Tic
    1.03
    Activations Density 0.018%

    No Known Activations