© 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. 18841
    Prev
    Next
    INDEX
    Explanations

    technical language and programming-related terms

    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
     mas
    -0.47
     mean
    -0.47
    nat
    -0.47
     '#'
    -0.46
    gnu
    -0.44
    digos
    -0.44
    nash
    -0.44
    ian
    -0.43
    INC
    -0.43
    StatusCodes
    -0.43
    POSITIVE LOGITS
    تقاوى
    0.76
    IVEREF
    0.76
     nahilalakip
    0.74
     Савезне
    0.71
    GEBURTSDATUM
    0.66
    出版年
    0.65
     Италијани
    0.65
     */
    0.65
     ujednoznacz
    0.63
    pperware
    0.61
    Activations Density 0.231%

    No Known Activations