© 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. 10357
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specifications or descriptions related to inventions and technology

    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
    liet
    -0.50
    rovna
    -0.50
    javas
    -0.48
    isela
    -0.46
    meja
    -0.46
    bogen
    -0.44
    собенно
    -0.44
    limmer
    -0.44
     CSS
    -0.43
     Shetty
    -0.43
    POSITIVE LOGITS
    ThroughAttribute
    0.71
     mergeFrom
    0.64
     unknownFields
    0.63
    InputTagHelper
    0.63
     includes
    0.59
     Includes
    0.59
     Incorpor
    0.59
     Dabei
    0.59
     incorporates
    0.59
     linkovi
    0.57
    Activations Density 0.192%

    No Known Activations