© 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. 6959
    Prev
    Next
    INDEX
    Explanations

    code snippets related to hardware configuration and effecting system-level changes

    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
    unistd
    -0.52
     Exactos
    -0.49
     Mentions
    -0.48
    новниш
    -0.47
    LayoutConstraint
    -0.47
    KommentareTeilen
    -0.47
     سبيل
    -0.46
    selas
    -0.46
    PRNewswire
    -0.45
     chancel
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.96
    DoubleQuotes
    0.69
    enterOuterAlt
    0.68
    featureID
    0.67
     متعلقه
    0.66
    SequentialGroup
    0.63
     विश्वसनीयता
    0.63
    zzleHttp
    0.62
    okovic
    0.59
     كومونز
    0.59
    Activations Density 0.128%

    No Known Activations