© 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. 17812
    Prev
    Next
    INDEX
    Explanations

    mathematical notation related to norms or absolute values

    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
    PerformLayout
    -0.65
    expandindo
    -0.65
    
    -0.64
     AssemblyCulture
    -0.63
     disponibilités
    -0.63
     coppia
    -0.60
    б
    -0.60
     numberWith
    -0.60
     ग्राहक
    -0.59
     CreateTagHelper
    -0.59
    POSITIVE LOGITS
    \|_{
    1.26
    \|_{\
    0.69
    |_{
    0.68
    httphttps
    0.64
    ficador
    0.63
    LUT
    0.63
    ://"
    0.63
     Trish
    0.62
    greenrobot
    0.61
    migrationBuilder
    0.61
    Activations Density 0.002%

    No Known Activations