© 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. 3726
    Prev
    Next
    INDEX
    Explanations

    patterns involving mathematical structures such as normalized matrices, limits, and polynomial inequalities

    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
     pouvoit
    -0.88
     auroit
    -0.85
     feroit
    -0.82
    altham
    -0.79
    amaño
    -0.78
     énergé
    -0.75
     ainfi
    -0.75
     cejas
    -0.73
    قایناق‌لار
    -0.73
    tiérrez
    -0.72
    POSITIVE LOGITS
    Vert
    2.94
     Vert
    1.99
     vert
    1.15
    vert
    0.98
     verts
    0.84
     verte
    0.73
    Verts
    0.67
    VERT
    0.66
     Verte
    0.66
    verti
    0.64
    Activations Density 0.011%

    No Known Activations