© 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. 10708
    Prev
    Next
    INDEX
    Explanations

    numerical values or references in the context of technical or scientific information

    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
     Meksiku
    -1.03
    XmlAccessorType
    -0.96
    oredCriteria
    -0.96
    djangoproject
    -0.94
     Ayr
    -0.91
    tinyos
    -0.89
     platelets
    -0.87
    etheless
    -0.85
    queryInterface
    -0.84
     NSCoder
    -0.82
    POSITIVE LOGITS
    Int
    1.12
     Int
    1.07
    いらっしゃ
    0.73
     maž
    0.71
     INT
    0.70
    ox
    0.68
     WorldCat
    0.68
    fare
    0.66
    тном
    0.66
    nt
    0.66
    Activations Density 0.020%

    No Known Activations