© 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. 3-RES-MATRYOSHKA-DC
    7. 81
    Prev
    Next
    INDEX
    Explanations

    technical terms related to design, development, and processes

    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
     hunne
    -0.81
    edicated
    -0.79
    "]));
    -0.78
     inéd
    -0.78
     ſeveral
    -0.77
     ")";
    -0.75
     ſmall
    -0.75
     ")");
    -0.74
    GRAFIA
    -0.73
     contemporanea
    -0.73
    POSITIVE LOGITS
     unit
    0.99
     segment
    0.98
     category
    0.98
     item
    0.98
     object
    0.98
     model
    0.96
     entity
    0.95
     device
    0.94
     area
    0.93
     event
    0.93
    Activations Density 18.523%

    No Known Activations