© 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. 6116
    Prev
    Next
    INDEX
    Explanations

    references to light behavior and interaction in optical 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
     newBuilder
    -0.47
     inflation
    -0.47
    紀
    -0.47
     dolci
    -0.46
    Meld
    -0.46
     wast
    -0.45
     gaseous
    -0.45
    !("{
    -0.44
    ⚖
    -0.44
     السياسية
    -0.44
    POSITIVE LOGITS
     Normdatei
    0.76
     scattering
    0.72
     виправивши
    0.72
    andReturn
    0.72
     समीक्षक
    0.71
     Scattering
    0.71
     BoxDecoration
    0.69
     оригіналу
    0.67
    verwijspagina
    0.67
    MENAFN
    0.67
    Activations Density 0.246%

    No Known Activations