© 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. 2044
    Prev
    Next
    INDEX
    Explanations

    information about figures in diagrams and the spouses of Japanese prime ministers

    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
    FROM
    -0.81
    AFTER
    -0.72
    WITH
    -0.69
    WHEN
    -0.67
    HERE
    -0.65
    BEFORE
    -0.63
    MANY
    -0.58
    WITHOUT
    -0.57
    EVERY
    -0.57
    WHERE
    -0.57
    POSITIVE LOGITS
     تضيفلها
    0.90
    __(/*!
    0.87
     mergeFrom
    0.73
    存于互联网档案馆
    0.73
    LikeLike
    0.72
    basicConfig
    0.70
    ChildScrollView
    0.68
    oneofs
    0.66
     Audiodateien
    0.66
    ANTLR
    0.65
    Activations Density 1.792%

    No Known Activations