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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 10870
    Prev
    Next
    INDEX
    Explanations

    specific structures or patterns in mathematical or technical expressions related to subsets and their properties

    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
    größern
    -0.55
    YOND
    -0.52
    δρ
    -0.50
     larga
    -0.48
     Liss
    -0.48
    lossus
    -0.48
     (;;
    -0.45
     beyond
    -0.45
    prehensive
    -0.45
     fancy
    -0.45
    POSITIVE LOGITS
     Smaller
    0.92
     smaller
    0.88
    OGND
    0.87
    Smaller
    0.87
    évaluateur
    0.83
     Peque
    0.82
    smaller
    0.76
     smallest
    0.74
    Small
    0.74
     скром
    0.73
    Activations Density 0.520%

    No Known Activations