© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24793
    Prev
    Next
    INDEX
    Explanations

    terms related to convexity in mathematical contexts

    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
    Negative Logits
     المعيارى
    -1.00
     Crot
    -0.86
    ništvo
    -0.85
    Pim
    -0.74
    JvmStatic
    -0.70
    ívar
    -0.70
    WindowConstants
    -0.70
    addGap
    -0.69
     Pim
    -0.69
    icoot
    -0.69
    POSITIVE LOGITS
     convex
    1.62
    Convex
    1.54
     Convex
    1.50
    convex
    1.47
    凸
    0.84
    Pyx
    0.74
     Khanna
    0.71
    )”.
    0.69
     Jensen
    0.68
    )');
    0.66
    Activations Density 0.002%

    No Known Activations