© 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. 22-RES-MATRYOSHKA-DC
    7. 2081
    Prev
    Next
    INDEX
    Explanations

    descriptions of brief expressions, animal noises, or fast movements

    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
    IntoConstraints
    -0.71
     transférez
    -0.62
     stood
    -0.61
    Standing
    -0.60
    ″]
    -0.59
    BagConstraints
    -0.59
     debout
    -0.58
    enumi
    -0.58
     Standing
    -0.57
    %";
    -0.56
    POSITIVE LOGITS
     look
    0.82
    look
    0.63
     LOOK
    0.62
     smirk
    0.60
     pose
    0.56
     Look
    0.56
     sneer
    0.53
     grin
    0.52
     espressione
    0.52
    Look
    0.52
    Activations Density 0.081%

    No Known Activations