© 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. 1674
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to sending or transmitting data

    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
    MigrationBuilder
    -0.77
    ArgsConstructor
    -0.66
    mybatisplus
    -0.60
    ukone
    -0.60
     Exists
    -0.59
     Anwar
    -0.58
     estimés
    -0.57
     arru
    -0.56
    TagMode
    -0.55
    apimachinery
    -0.55
    POSITIVE LOGITS
     transmits
    1.10
     transmit
    1.09
     sends
    1.05
     transmitting
    1.05
     Sends
    1.02
     transmitted
    1.01
    sendData
    1.00
    transmit
    0.99
    emit
    0.91
     Delivered
    0.91
    Activations Density 1.134%

    No Known Activations