© 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. 24-RES-MATRYOSHKA-DC
    7. 1213
    Prev
    Next
    INDEX
    Explanations

    code related to matrix operations, especially those operating on the lower triangle with optional diagonal preconditioner

    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/blocks.24.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.24.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
     snippetHide
    -0.82
    AndEndTag
    -0.82
     GenerationType
    -0.75
     cherchés
    -0.70
     HttpNotFound
    -0.70
     protoimpl
    -0.68
    featureID
    -0.68
    Хьажоргаш
    -0.67
    IsContent
    -0.66
    PreferredItem
    -0.66
    POSITIVE LOGITS
     work
    0.47
     */
    0.47
     subroutine
    0.46
    లాలు
    0.46
     mát
    0.45
    alam
    0.45
     .
    0.45
     real
    0.45
     calls
    0.43
     Work
    0.42
    Activations Density 0.183%

    No Known Activations