© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15519
    Prev
    Next
    INDEX
    Explanations

    structured, repetitive, or formatted code segments and their associated elements

    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
     er
    -0.66
     rest
    -0.61
    .
    -0.60
     b
    -0.59
     on
    -0.59
     y
    -0.58
     w
    -0.57
     n
    -0.57
     (
    -0.57
    ,
    -0.57
    POSITIVE LOGITS
     itſelf
    1.35
     Majefty
    1.30
     myſelf
    1.29
     Monfieur
    1.27
     ſeveral
    1.23
     purpoſe
    1.21
     himſelf
    1.17
     Efq
    1.17
     themſelves
    1.14
     neceff
    1.13
    Activations Density 0.796%

    No Known Activations