© 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. 12-RES-MATRYOSHKA-DC
    7. 18488
    Prev
    Next
    INDEX
    Explanations

    references to Lagrange multipliers and related mathematical concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ellington
    -0.97
    __":
    -0.76
    __':
    -0.72
    ']")
    -0.71
     Svet
    -0.70
     Sze
    -0.69
     Hummel
    -0.69
     houſe
    -0.66
    ...',
    -0.66
    : 
    -0.65
    POSITIVE LOGITS
    Lag
    1.35
     Lag
    1.27
     lag
    1.18
    lag
    1.10
     Lagrange
    0.97
    LAG
    0.95
     LAG
    0.93
     Lagrangian
    0.92
     lags
    0.84
    Laguna
    0.84
    Activations Density 0.002%

    No Known Activations