© 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. 16854
    Prev
    Next
    INDEX
    Explanations

    information related to data structures and metadata

    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
    WebServlet
    -0.93
    verwijspagina
    -0.92
    LookAnd
    -0.85
    rrggbb
    -0.82
    DockStyle
    -0.82
    Begriffsklä
    -0.81
    ьаж
    -0.79
    IsMutable
    -0.74
    WithIOException
    -0.73
    expandindo
    -0.70
    POSITIVE LOGITS
     information
    0.65
    information
    0.60
     informations
    0.56
     parle
    0.56
    akterysty
    0.56
    Information
    0.55
    informations
    0.51
     información
    0.50
     informações
    0.49
     информацию
    0.49
    Activations Density 0.215%

    No Known Activations