© 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. 2776
    Prev
    Next
    INDEX
    Explanations

    the usage of the word "connected" in both english and french

    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
     '\\;'
    -0.84
    PreferredItem
    -0.82
    ItemBackground
    -0.81
     protoimpl
    -0.73
    MessageOf
    -0.70
    encodeWith
    -0.70
    RegressionTest
    -0.69
     propOrder
    -0.68
    SharedCtor
    -0.68
    principalColumn
    -0.68
    POSITIVE LOGITS
     connect
    3.08
     connection
    3.05
     connecting
    2.88
     connects
    2.84
    connect
    2.70
     Connect
    2.67
     connected
    2.64
     connections
    2.63
     Connection
    2.63
    connection
    2.58
    Activations Density 0.589%

    No Known Activations