© 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. 93
    Prev
    Next
    INDEX
    Explanations

    descriptions of mechanical components of machines, in particular anything with wheels

    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
    IndentedString
    -0.66
    NameInMap
    -0.62
     dodgy
    -0.61
     oficial
    -0.60
     unofficial
    -0.60
     shady
    -0.57
     GENERATED
    -0.57
     kasarigan
    -0.57
    IMPORTED
    -0.56
     desapare
    -0.56
    POSITIVE LOGITS
     thereto
    0.91
     embodiments
    0.91
     preferably
    0.84
     substantially
    0.83
     wherein
    0.82
     herein
    0.82
     therefrom
    0.77
     Preferably
    0.75
     disclosed
    0.74
     thereof
    0.74
    Activations Density 6.089%

    No Known Activations