© 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. 1526
    Prev
    Next
    INDEX
    Explanations

    HTML input elements within UI structure

    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
    scrapy
    -0.60
    SpringRunner
    -0.57
    QtCore
    -0.52
     ?>">
    -0.51
     autorytatywna
    -0.51
    stitch
    -0.51
     HomeController
    -0.51
    TintColor
    -0.51
     Contingency
    -0.51
     placental
    -0.51
    POSITIVE LOGITS
     input
    0.93
    input
    0.82
     Input
    0.77
    Input
    0.73
     getInput
    0.72
    InputTagHelper
    0.71
     inputs
    0.70
     TextEditing
    0.69
     INPUT
    0.68
    输入
    0.67
    Activations Density 0.989%

    No Known Activations