© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1090
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms related to scientific and technical research

    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
     mål
    -0.38
     Deixe
    -0.37
     irré
    -0.36
     skydd
    -0.35
    扶
    -0.35
     怎样
    -0.35
    bex
    -0.34
     iklan
    -0.34
     simplifié
    -0.34
    hatian
    -0.34
    POSITIVE LOGITS
    IndentedString
    1.00
    AsUp
    0.98
    RenderAtEndOf
    0.96
    Tembelea
    0.95
     &___
    0.92
     lenker
    0.90
    UnsafeEnabled
    0.83
     HasFactory
    0.79
    queryInterface
    0.79
    IUrlHelper
    0.79
    Activations Density 0.164%

    No Known Activations