© 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. 20631
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "Flamingo" and its various forms or variations

    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
    Negative Logits
    &+
    -0.78
    ‌ی
    -0.73
    一个
    -0.67
    ListPage
    -0.66
    こと
    -0.65
    Dieter
    -0.65
     Pires
    -0.63
     Clive
    -0.63
    Porto
    -0.63
    isson
    -0.61
    POSITIVE LOGITS
     Fla
    1.67
    Fla
    1.58
     Flair
    1.52
     FLA
    1.34
     flaps
    1.30
     flares
    1.25
     Flames
    1.23
     fla
    1.21
     NSCoder
    1.20
    fla
    1.16
    Activations Density 0.011%

    No Known Activations