© 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. 3402
    Prev
    Next
    INDEX
    Explanations

    references to specific implementation-related scripts or code snippets

    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
    initializeApp
    -0.60
    CIR
    -0.57
    pannt
    -0.56
    ļas
    -0.56
    hause
    -0.54
     waard
    -0.54
    łek
    -0.52
     ķ
    -0.52
    agues
    -0.52
    $^
    -0.52
    POSITIVE LOGITS
    ie
    3.25
    IE
    3.05
     IE
    2.34
     ie
    2.17
    ies
    1.82
    Ie
    1.76
    rie
    1.56
    IES
    1.55
     Ie
    1.54
    ieg
    1.49
    Activations Density 0.065%

    No Known Activations