© 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. 25386
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications and scientific measurements

    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
     kív
    -0.52
     wasn
    -0.52
     vuol
    -0.51
    互
    -0.45
     isn
    -0.45
     mė
    -0.45
     Planta
    -0.45
     turb
    -0.44
    mathrm
    -0.43
    ื
    -0.43
    POSITIVE LOGITS
    featureID
    1.04
    :✨
    1.00
     AssemblyCulture
    0.91
    +#+#
    0.88
    GEBURTSDATUM
    0.87
    verwijspagina
    0.86
    aarrggbb
    0.84
    mergeFrom
    0.82
    astéroïdes
    0.81
     pinulongan
    0.80
    Activations Density 0.062%

    No Known Activations