© 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. 30653
    Prev
    Next
    INDEX
    Explanations

    references to the speaker and their personal experiences or statements

    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
    makeConstraints
    -0.75
    脚注の使い方
    -0.73
     BorderRadius
    -0.69
    CGRectMake
    -0.69
    ViewFeatures
    -0.69
    føring
    -0.69
    出版年
    -0.68
    WaitGroup
    -0.68
     GenerationType
    -0.67
    MenuInflater
    -0.67
    POSITIVE LOGITS
     Jag
    0.79
     jag
    0.66
    Jag
    0.64
    jag
    0.61
     vues
    0.59
    pablo
    0.59
    sampler
    0.57
    roek
    0.57
    ousands
    0.56
     vill
    0.55
    Activations Density 0.015%

    No Known Activations