© 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. 1562
    Prev
    Next
    INDEX
    Explanations

    computer networking code and error messages

    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
    jago
    -0.61
     समीक्षाओं
    -0.60
    Personendaten
    -0.56
    ContentAsync
    -0.55
     betweenstory
    -0.54
    isContained
    -0.50
     florales
    -0.50
    DotNetBar
    -0.50
    osaurs
    -0.49
     aisles
    -0.49
    POSITIVE LOGITS
     connection
    1.15
     Connection
    1.06
     TCP
    1.04
    connection
    1.02
     connect
    1.02
    Connection
    1.02
     connections
    1.01
     socket
    0.96
     connecting
    0.94
    connect
    0.94
    Activations Density 1.466%

    No Known Activations