© 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. 3286
    Prev
    Next
    INDEX
    Explanations

    expressions involving quadratic and statistical functions

    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
     CreateTagHelper
    -0.84
     rem
    -0.66
    !\!\
    -0.65
    irsk
    -0.62
     trich
    -0.60
     bek
    -0.59
    setResizable
    -0.58
    tré
    -0.57
     Trier
    -0.55
     Ank
    -0.54
    POSITIVE LOGITS
    quad
    3.03
     quad
    1.66
    Quad
    1.61
     Quad
    1.55
    QUAD
    1.39
     quads
    1.21
    qquad
    1.02
     quadrant
    1.02
     quadru
    1.00
     cuad
    0.94
    Activations Density 0.014%

    No Known Activations