© 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. 2-RES-MATRYOSHKA-DC
    7. 2440
    Prev
    Next
    INDEX
    Explanations

    references to software licenses and license content

    oai_token-act-pair · gpt-4.1-nano
    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
    +#+
    -0.80
    OGND
    -0.73
    JsonInclude
    -0.69
     "..\..\
    -0.65
    XmlAccessorType
    -0.65
     disambiguazione
    -0.63
    +#+#
    -0.61
     ujednoznacz
    -0.61
    Viitteet
    -0.60
    MigrationBuilder
    -0.58
    POSITIVE LOGITS
     distributed
    3.03
     Distributed
    2.70
    distributed
    2.66
    Distributed
    2.53
     distribute
    1.41
     distributes
    1.34
     Distribute
    1.34
     dispersed
    1.32
     DISTRIB
    1.22
     decentralized
    1.20
    Activations Density 0.019%

    No Known Activations