© 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. 3068
    Prev
    Next
    INDEX
    Explanations

    references to retrograde processes or retro activities

    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
    Datuak
    -0.61
    Diwedd
    -0.60
    ufact
    -0.59
     horário
    -0.59
    Geplaatst
    -0.57
     evangé
    -0.57
     prossimo
    -0.56
    isContained
    -0.56
     giornal
    -0.56
    がて
    -0.56
    POSITIVE LOGITS
    retro
    3.17
     retro
    3.11
    Retro
    2.98
     Retro
    2.86
     retrospec
    2.16
     rétro
    2.09
     retrospective
    2.00
     retroactive
    1.91
     Retrospective
    1.77
    レトロ
    1.48
    Activations Density 0.016%

    No Known Activations