© 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. 26513
    Prev
    Next
    INDEX
    Explanations

    references to omissions or missing information

    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
    MemoryWarning
    -0.80
    таратура
    -0.80
    IsMutable
    -0.80
    ::::::::
    -0.79
    MigrationBuilder
    -0.79
    gameserver
    -0.79
    aarrggbb
    -0.78
     cherchés
    -0.77
    AsUp
    -0.75
    setVerticalGroup
    -0.73
    POSITIVE LOGITS
     omission
    1.18
     omit
    1.03
     omissions
    1.00
     omitting
    1.00
     omits
    0.98
     omitted
    0.96
    omit
    0.81
     withheld
    0.73
     withhold
    0.70
     Huxley
    0.70
    Activations Density 0.005%

    No Known Activations