© 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. 6-RES-MATRYOSHKA-DC
    7. 148
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    oai_token-act-pair · gemini-2.0-flash
    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
     سكانية
    -0.84
    ">//
    -0.76
    ึ้น
    -0.69
    ugeot
    -0.66
     ")[
    -0.65
    ENIX
    -0.64
    ?}",
    -0.63
    nabis
    -0.63
    eapple
    -0.62
    ïlande
    -0.62
    POSITIVE LOGITS
    AddTagHelper
    0.79
     Italijanski
    0.65
    المناصب
    0.65
    aarrggbb
    0.64
    يكب
    0.61
    kháu
    0.60
     betweenstory
    0.60
     muchacho
    0.60
     morire
    0.59
     majeurs
    0.58
    Activations Density 2.272%

    No Known Activations