© 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. 12-RES-MATRYOSHKA-DC
    4. 460
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific symbols

    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
    numRows
    -0.67
     fran
    -0.65
     cara
    -0.62
    tps
    -0.61
     tup
    -0.61
    msm
    -0.60
    ViewFeatures
    -0.60
    respond
    -0.59
     pan
    -0.58
    ondy
    -0.57
    POSITIVE LOGITS
    $;
    1.16
    _;
    1.13
    ;;;
    1.05
    ;;;;
    1.03
    icolon
    1.02
    _;
    
    0.97
    +;
    0.96
    .;
    0.95
    >>();
    0.94
    }$;
    0.92
    Activations Density 1.271%

    No Known Activations