© 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. 1915
    Prev
    Next
    INDEX
    Explanations

    the presence of LaTeX package commands related to mathematical typesetting

    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
    /***/
    -1.08
     pinulongan
    -1.05
    TagMode
    -1.04
    出版年
    -1.04
     nahilalakip
    -1.04
    AddHtmlAttribute
    -1.02
    脚注の使い方
    -1.02
     resourceCulture
    -0.98
    rungsseite
    -0.97
    ChildScrollView
    -0.97
    POSITIVE LOGITS
    ams
    1.11
     AMS
    0.92
     ams
    0.84
    AMS
    0.79
     Ams
    0.68
    AM
    0.60
     ziua
    0.59
     toată
    0.56
    aminen
    0.53
     prieten
    0.52
    Activations Density 0.001%

    No Known Activations