© 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. 32156
    Prev
    Next
    INDEX
    Explanations

    technical terms and formatting related to debugging or programming structures

    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
     lenker
    -0.73
    Билгалдахарш
    -0.73
    asteroide
    -0.70
    حوالہ
    -0.66
     Infórmanos
    -0.66
    Revenir
    -0.65
     muualla
    -0.64
     autorytatywna
    -0.61
     utafitiHapana
    -0.61
    Lähteet
    -0.61
    POSITIVE LOGITS
    endregion
    0.68
     rosse
    0.54
    ThroughAttribute
    0.51
    ovac
    0.49
     ویکی‌پدیا
    0.48
    ImageIO
    0.47
    gesehen
    0.47
    dientemente
    0.47
     exécu
    0.46
     Horm
    0.45
    Activations Density 0.274%

    No Known Activations