© 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. 20840
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical grounding

    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
     topsoil
    -0.98
     ویکی‌پدیا
    -0.97
     HasFactory
    -0.96
    createCell
    -0.93
    sizeCache
    -0.93
    EDEFAULT
    -0.93
     Didier
    -0.92
     umani
    -0.91
     Torr
    -0.90
     Charts
    -0.88
    POSITIVE LOGITS
    Grind
    0.77
     grund
    0.70
     Grind
    0.70
    ズム
    0.66
    ceaux
    0.63
    grou
    0.62
    точно
    0.60
    Grounded
    0.59
     grounds
    0.58
    ジング
    0.58
    Activations Density 0.015%

    No Known Activations