© 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. 15675
    Prev
    Next
    INDEX
    Explanations

    numerical values and data structures related to technical specifications

    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
    DotNetBar
    -0.86
    WEAR
    -0.86
     onAnimation
    -0.84
     MainAxisSize
    -0.82
    branches
    -0.80
     MessageBoxIcon
    -0.80
    رشف
    -0.78
    thmetic
    -0.77
    anueva
    -0.77
    Aç
    -0.76
    POSITIVE LOGITS
     pylint
    0.69
     Pus
    0.68
    躇
    0.65
     PUT
    0.64
     putt
    0.64
    Pus
    0.63
    si
    0.62
     Pilgri
    0.62
    ील
    0.62
     makl
    0.61
    Activations Density 0.333%

    No Known Activations