© 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. 22-RES-MATRYOSHKA-DC
    7. 1166
    Prev
    Next
    INDEX
    Explanations

    technical terms related to signal processing, electronics, and manufacturing

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     Audiodateien
    -0.76
    invokeLater
    -0.63
    WriteTagHelper
    -0.61
    出版年
    -0.55
     незавершена
    -0.55
    хьтан
    -0.54
     démarche
    -0.50
     thèse
    -0.50
    DMETHOD
    -0.48
    bootstrapcdn
    -0.48
    POSITIVE LOGITS
     device
    0.92
     apparatus
    0.86
     unit
    0.82
     equipment
    0.78
    device
    0.76
     devices
    0.71
    devise
    0.71
     Apparatus
    0.70
    unit
    0.70
     Device
    0.70
    Activations Density 1.516%

    No Known Activations