© 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. 20145
    Prev
    Next
    INDEX
    Explanations

    symbols that resemble accents or special characters

    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
     bag
    -0.81
    WindowConstants
    -0.78
     bags
    -0.75
    Penguin
    -0.67
    JScrollPane
    -0.67
    ('../../../
    -0.66
    ystis
    -0.66
    gouv
    -0.65
     Bag
    -0.65
     hasNext
    -0.65
    POSITIVE LOGITS
    ¨
    1.52
     ¨
    1.11
    〗
    0.84
     Elegance
    0.73
    ISupport
    0.70
     ESE
    0.70
    ˙
    0.66
    cense
    0.65
    …”
    0.64
     reticulum
    0.64
    Activations Density 0.001%

    No Known Activations