© 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. 24475
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical methods and algorithms, particularly focused on efficiency and stability

    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
     plus
    -0.54
     apropri
    -0.48
     affirm
    -0.45
     Plus
    -0.44
     sella
    -0.44
     препратки
    -0.42
    writeValue
    -0.42
    Plus
    -0.42
     apropi
    -0.42
    mergeFrom
    -0.42
    POSITIVE LOGITS
    出版年
    0.81
    __':
    0.76
    __":
    0.74
     nakalista
    0.71
    ArrowToggle
    0.70
    ...');
    0.70
    JspWriter
    0.68
    ){}
    0.68
    ...");
    0.67
     mergeFrom
    0.67
    Activations Density 0.015%

    No Known Activations