© 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. 784
    Prev
    Next
    INDEX
    Explanations

    references to software updates

    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
     ویکی‌پدیای
    -0.71
    Personendaten
    -0.68
    StoryboardSegue
    -0.65
    rungsseite
    -0.60
    ionario
    -0.58
    converters
    -0.56
    хьтан
    -0.56
     jadx
    -0.54
     ProtoMessage
    -0.54
    NOPQRST
    -0.53
    POSITIVE LOGITS
     update
    4.19
     Update
    3.94
    update
    3.75
    Update
    3.70
     updates
    3.56
     UPDATE
    3.52
     updating
    3.47
     Updates
    3.39
    UPDATE
    3.20
     updated
    3.17
    Activations Density 0.083%

    No Known Activations