© 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. 22541
    Prev
    Next
    INDEX
    Explanations

    references to colors and foreground/background settings in a programming or user interface context

    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
     Colla
    -0.63
    veret
    -0.57
     озеро
    -0.56
    Burt
    -0.56
    ジュアル
    -0.55
     clicar
    -0.54
    7
    -0.54
    int
    -0.54
     nhau
    -0.54
     själ
    -0.53
    POSITIVE LOGITS
     FG
    1.22
     foreground
    1.21
     fg
    1.06
    foreground
    1.01
    fg
    1.00
    Fg
    0.98
    Foreground
    0.93
    FG
    0.90
     Fg
    0.86
    guous
    0.85
    Activations Density 0.002%

    No Known Activations