© 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. 2169
    Prev
    Next
    INDEX
    Explanations

    mathematical notation for spacing

    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
     CreateTagHelper
    -0.67
     rem
    -0.62
    insic
    -0.60
    enumi
    -0.59
     كومونز
    -0.57
    Namara
    -0.57
    towych
    -0.57
    ThroughAttribute
    -0.57
     btn
    -0.56
     Erick
    -0.56
    POSITIVE LOGITS
    quad
    2.61
    Quad
    1.55
     Quad
    1.53
     quad
    1.49
    QUAD
    1.30
     quadru
    1.20
     quads
    1.16
     quadrant
    1.06
    qquad
    1.05
     Quadrant
    1.01
    Activations Density 0.009%

    No Known Activations