© 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. 30708
    Prev
    Next
    INDEX
    Explanations

    formatted references or citations 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
     pu
    -0.52
    不可
    -0.47
    ↵↵
    -0.47
     lopp
    -0.47
    pu
    -0.46
     sommer
    -0.46
     cho
    -0.46
     saper
    -0.46
    少
    -0.45
     quanto
    -0.44
    POSITIVE LOGITS
     يتيمه
    0.98
     виправивши
    0.98
    yntaxException
    0.97
    Personensuche
    0.93
     CreateTagHelper
    0.92
     дописавши
    0.88
     AssemblyCulture
    0.86
    niająca
    0.86
    verwijspagina
    0.84
    клопе
    0.81
    Activations Density 0.091%

    No Known Activations