© 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. 8384
    Prev
    Next
    INDEX
    Explanations

    references to shelves or shelving

    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
     disponibilités
    -0.86
    Aiheesta
    -0.85
     estimés
    -0.82
     honra
    -0.77
     Pittman
    -0.74
     Garnet
    -0.72
     Rush
    -0.70
    jooq
    -0.69
    COUP
    -0.69
    PRWEB
    -0.69
    POSITIVE LOGITS
     shelf
    1.60
     shelves
    1.51
     Shelf
    1.49
    shelf
    1.42
     Shelves
    1.36
    Shelf
    1.34
     shel
    1.27
    Shel
    1.24
     Shel
    1.17
     shelving
    1.10
    Activations Density 0.003%

    No Known Activations