© 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. 26605
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "fmt" related to formatting functions in programming

    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
    Hab
    -0.76
    者
    -0.74
     Hab
    -0.73
     hab
    -0.69
    rungsseite
    -0.66
    ✭✭
    -0.65
    ✪
    -0.63
    <strong>
    -0.63
    via
    -0.62
    RTEX
    -0.62
    POSITIVE LOGITS
    fmt
    1.55
     fmt
    1.47
     Gump
    0.81
    RenderAtEndOf
    0.80
    :✨
    0.73
     Cheshire
    0.73
    sni
    0.70
     Tir
    0.69
    annique
    0.68
    Lähteet
    0.67
    Activations Density 0.001%

    No Known Activations