© 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. 551
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing exclusivity or specific restrictions

    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
    \{\\
    -0.98
    :✨
    -0.83
    ViewFeatures
    -0.82
     AssemblyCulture
    -0.81
    ///**
    -0.77
    RegressionTest
    -0.76
    //});
    -0.73
     myſelf
    -0.73
    ++];
    -0.73
    Xna
    -0.72
    POSITIVE LOGITS
     only
    1.58
    only
    1.37
     Only
    1.34
    Only
    1.28
     ONLY
    1.27
    ONLY
    1.19
     лишь
    1.02
     seules
    0.95
     alleen
    0.95
     только
    0.94
    Activations Density 0.826%

    No Known Activations