© 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. 6-RES-MATRYOSHKA-DC
    7. 1536
    Prev
    Next
    INDEX
    Explanations

    words, acronyms, or names related to organizations or projects related to health, finance, physics, or coding

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    adaptiveStyles
    -0.81
    AsUp
    -0.81
    tacles
    -0.74
    Bian
    -0.72
    ItemBackground
    -0.70
     Klasse
    -0.70
    czaj
    -0.69
    蟹
    -0.69
    Obrázky
    -0.68
     JAXBElement
    -0.68
    POSITIVE LOGITS
     COR
    1.12
    mor
    1.09
     MOR
    1.07
    por
    1.05
     LOR
    1.05
    lor
    1.02
    oro
    1.02
    ror
    1.01
    POR
    1.01
     KOR
    1.01
    Activations Density 2.306%

    No Known Activations