© 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. 2-RES-MATRYOSHKA-DC
    7. 3070
    Prev
    Next
    INDEX
    Explanations

    references to specific intervention or treatment reports

    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
    ratore
    -0.57
    ators
    -0.56
    UserScript
    -0.54
    ConstraintMaker
    -0.50
    ational
    -0.50
    enumi
    -0.49
    atimes
    -0.49
     comets
    -0.48
    Kontrola
    -0.47
    ations
    -0.47
    POSITIVE LOGITS
    ate
    2.64
    ATE
    1.98
    erate
    1.09
    Ate
    1.02
     Ate
    1.00
    iate
    0.94
    atee
    0.91
    orate
    0.90
    nate
    0.88
     ATE
    0.88
    Activations Density 0.023%

    No Known Activations