© 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. 6051
    Prev
    Next
    INDEX
    Explanations

    numerical or coded data relevant to a structured format or system

    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
    GEBURTS
    -0.66
    enumi
    -0.63
     BorderRadius
    -0.63
    InstrumentedTest
    -0.59
    Personensuche
    -0.58
     ujednoznacz
    -0.58
    ngdoc
    -0.57
     Exo
    -0.56
     CURIAM
    -0.55
    verwijspagina
    -0.55
    POSITIVE LOGITS
    ECAUSE
    0.47
     zák
    0.45
    stø
    0.45
    ęb
    0.44
     disponibilités
    0.44
     おもちゃ
    0.43
     zależ
    0.43
    Уже
    0.43
    并
    0.43
     gebru
    0.43
    Activations Density 0.103%

    No Known Activations