© 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. 6508
    Prev
    Next
    INDEX
    Explanations

    references to code import statements

    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
     autorytatywna
    -0.85
    Спасылкі
    -0.69
    ագրություններ
    -0.69
    interopRequire
    -0.68
    msgTypes
    -0.68
    TagHelper
    -0.68
    туга
    -0.67
    InjectAttribute
    -0.66
     تضيفلها
    -0.66
     useParams
    -0.64
    POSITIVE LOGITS
    ps
    3.25
    PS
    2.23
     ps
    2.06
     PS
    1.78
     Ps
    1.48
    Ps
    1.40
    IPS
    1.26
    aps
    1.19
    пс
    1.15
    APS
    1.08
    Activations Density 0.041%

    No Known Activations