© 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. 3442
    Prev
    Next
    INDEX
    Explanations

    references to the process of reverse transcription or reverse transcription-related 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
     فريبيس
    -0.56
     against
    -0.55
    inkle
    -0.52
    Искәрмәләр
    -0.49
    Hutch
    -0.49
    rdı
    -0.48
     Gutierrez
    -0.48
    WaitGroup
    -0.48
    utte
    -0.47
     urllib
    -0.47
    POSITIVE LOGITS
     reverse
    3.78
     Reverse
    3.53
    reverse
    3.36
    Reverse
    3.34
     reverses
    2.86
     reversed
    2.83
     reversing
    2.58
     reversal
    2.45
    reversed
    2.36
     revers
    2.28
    Activations Density 0.032%

    No Known Activations