© 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. 2319
    Prev
    Next
    INDEX
    Explanations

    the word "equation" or "equations"

    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
     button
    -1.05
     buttons
    -1.02
     Button
    -1.00
    Button
    -0.96
    button
    -0.88
     Buttons
    -0.88
    buttons
    -0.84
     BUTTON
    -0.80
     botón
    -0.76
     botão
    -0.76
    POSITIVE LOGITS
     equation
    1.79
     equations
    1.49
    equation
    1.32
     Equation
    1.28
    Equation
    1.27
    equations
    1.22
     Equations
    1.14
    Equations
    1.11
     <=",
    1.03
     eqn
    0.88
    Activations Density 0.011%

    No Known Activations