© 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. 223
    Prev
    Next
    INDEX
    Explanations

    URLs and web addresses within the document

    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
    âmara
    -0.52
    Kanpo
    -0.51
    Оста
    -0.50
    SharedCtor
    -0.50
    soort
    -0.50
     kör
    -0.49
    kör
    -0.49
     Balo
    -0.49
    ativement
    -0.48
    LookAnd
    -0.47
    POSITIVE LOGITS
    ://
    5.69
    ://"
    3.58
    :\/\/
    2.58
    :///
    2.39
    ://$
    2.33
    ="//
    1.84
    :/
    1.27
    ">//
    0.98
    www
    0.94
     "//
    0.94
    Activations Density 0.039%

    No Known Activations