© 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. 6989
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    __)
    -0.62
    תודה
    -0.62
    UDC
    -0.60
    ์ตูน
    -0.59
     ethically
    -0.59
    WebServlet
    -0.59
     Zwick
    -0.59
     Crum
    -0.58
    umball
    -0.57
    Hozzáférés
    -0.57
    POSITIVE LOGITS
    •
    2.05
    newArrayList
    0.70
    MessageTagHelper
    0.65
    ✨:
    0.62
     jLabel
    0.61
     PropTypes
    0.59
    lyk
    0.59
     kait
    0.57
     Jat
    0.56
     inade
    0.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.