© 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. 17275
    Prev
    Next
    INDEX
    Explanations

    references to citations or bibliographic entries in academic writing

    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
    ंदीखरीदारी
    -1.11
     Faker
    -0.87
    fjspx
    -0.84
    Faker
    -0.83
    findpost
    -0.82
     Económica
    -0.82
     оригіналу
    -0.82
     AssemblyProduct
    -0.82
    tagHelper
    -0.81
    Datuak
    -0.81
    POSITIVE LOGITS
    [[
    1.18
     [[
    1.09
     Mang
    0.68
    Mang
    0.65
    ([[
    0.63
     teng
    0.60
    =[[
    0.59
    ags
    0.59
     dring
    0.58
    ilh
    0.56
    Activations Density 0.003%

    No Known Activations