© 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. 1-RES-MATRYOSHKA-DC
    7. 497
    Prev
    Next
    INDEX
    Explanations

    mentions of recent or newly introduced items or concepts

    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
    INSEE
    -0.59
    ніципалі
    -0.57
    jstor
    -0.57
     GetComponent
    -0.56
     ItemStack
    -0.56
     getParent
    -0.55
    eficent
    -0.55
    siger
    -0.54
    IBAction
    -0.54
     uParam
    -0.54
    POSITIVE LOGITS
     new
    4.50
    new
    4.03
     New
    3.17
    New
    3.11
     NEW
    3.11
     nueva
    3.05
     nieuwe
    2.98
    新
    2.97
    NEW
    2.95
     neue
    2.94
    Activations Density 0.660%

    No Known Activations