© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 32578
    Prev
    Next
    INDEX
    Explanations

    complex sentence structures in English

    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
    Negative Logits
    DockStyle
    -0.54
     Kości
    -0.50
    FieldOffset
    -0.49
     agrarian
    -0.47
    golf
    -0.47
     चीज़ों
    -0.47
    illig
    -0.47
    帰り
    -0.45
     trå
    -0.45
     registered
    -0.44
    POSITIVE LOGITS
    SharedDtor
    0.71
    SequentialGroup
    0.68
    InjectAttribute
    0.66
     Infórmanos
    0.66
    ⓧ
    0.65
    хьтан
    0.65
     հղումներ
    0.65
     שוליים
    0.63
    uxxxx
    0.62
    webElementXpaths
    0.61
    Activations Density 0.045%

    No Known Activations