© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13969
    Prev
    Next
    INDEX
    Explanations

    references to specific technical identifiers or labels related to structured data, hardware components, or software modules

    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
     useStyles
    -0.70
    bootstrapcdn
    -0.66
     TestBed
    -0.64
     useAppContext
    -0.63
    prepareStatement
    -0.62
    €)
    -0.62
    )";
    -0.61
    Gambas
    -0.60
    ")));
    -0.60
     Paar
    -0.59
    POSITIVE LOGITS
    ota
    3.66
    OTA
    2.19
    otas
    1.57
     ota
    0.99
     OTA
    0.90
    kota
    0.77
     Ota
    0.66
    وتا
    0.60
    uta
    0.60
    Ota
    0.60
    Activations Density 0.000%

    No Known Activations