© 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. 5434
    Prev
    Next
    INDEX
    Explanations

    phrase constructions that introduce or emphasize important points

    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
    ußer
    -0.52
    endregion
    -0.52
     enkelte
    -0.50
    ?,?,
    -0.50
    setContentType
    -0.47
    borgen
    -0.47
    mockito
    -0.46
     recent
    -0.45
     boven
    -0.45
    مؤ
    -0.45
    POSITIVE LOGITS
     lenker
    0.98
    出版年
    0.90
    webElementXpaths
    0.75
    BufferException
    0.73
     nahilalakip
    0.73
    endphp
    0.72
    AddTagHelper
    0.71
    
    0.70
    atecas
    0.69
    achusetts
    0.69
    Activations Density 0.195%

    No Known Activations