© 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. 12-RES-MATRYOSHKA-DC
    7. 774
    Prev
    Next
    INDEX
    Explanations

    terms related to efficiency and optimization processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.76
    ArgsConstructor
    -0.69
     ProtoMessage
    -0.66
    AndEndTag
    -0.50
    fige
    -0.50
    ptest
    -0.50
     onCancelled
    -0.50
    RenderAtEndOf
    -0.49
     himo
    -0.48
    GeneratedMessage
    -0.47
    POSITIVE LOGITS
     effectively
    0.69
    ToAction
    0.66
     efficacement
    0.65
     efficiently
    0.63
     meglio
    0.63
     safer
    0.62
    kannt
    0.62
     smoother
    0.62
     better
    0.61
    öglichkeiten
    0.61
    Activations Density 3.249%

    No Known Activations