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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 28520
    Prev
    Next
    INDEX
    Explanations

    statistical data and numerical representations in research studies

    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
    #![
    -0.52
    XHR
    -0.47
    R
    -0.47
    G
    -0.46
      
    -0.46
    Diweddarwch
    -0.46
    D
    -0.44
     ||
    -0.41
     //
    -0.41
    A
    -0.41
    POSITIVE LOGITS
     autorytatywna
    0.98
    Portály
    0.90
    Datuak
    0.88
     contextLoads
    0.87
    expandindo
    0.84
    ftagPool
    0.84
    Parcelize
    0.83
    parsedMessage
    0.80
     Chwiliwch
    0.79
     تضيفلها
    0.79
    Activations Density 0.024%

    No Known Activations