© 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
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13359
    Prev
    Next
    INDEX
    Explanations

    references to specific sequential steps or stages in a process

    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
    forChild
    -0.71
    esgue
    -0.63
    astify
    -0.60
     near
    -0.59
    UTERS
    -0.57
    bootstrapcdn
    -0.57
     beside
    -0.56
    iastes
    -0.55
    forName
    -0.54
     محفوظة
    -0.54
    POSITIVE LOGITS
     Next
    1.92
    Next
    1.55
    ModelSerializer
    0.81
    Then
    0.71
    then
    0.67
     NEXT
    0.66
     then
    0.65
     então
    0.62
    IsContent
    0.62
     Then
    0.60
    Activations Density 0.003%

    No Known Activations