© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 3893
    Prev
    Next
    INDEX
    Explanations

    references to Maven build system components, such as plugins and artifact identifiers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.62
     createState
    -0.57
     "..\..\..\
    -0.57
    مقاله
    -0.56
    ManagedBean
    -0.55
     snippetHide
    -0.54
    dataIndex
    -0.54
     Echt
    -0.53
    WriteTagHelper
    -0.52
     sala
    -0.52
    POSITIVE LOGITS
    zip
    1.02
    ZIP
    0.96
     zip
    0.95
     ZIP
    0.93
     zipfile
    0.92
    Zip
    0.84
     Zip
    0.84
    jar
    0.77
    tgz
    0.73
    JAR
    0.73
    Activations Density 0.679%

    No Known Activations