© 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. 1-RES-MATRYOSHKA-DC
    7. 830
    Prev
    Next
    INDEX
    Explanations

    information related to memory addressing and transfer protocols

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     approach
    -0.67
     approaches
    -0.65
     APPROACH
    -0.62
    approach
    -0.59
    protoimpl
    -0.59
     avvic
    -0.59
     Approach
    -0.57
     approche
    -0.57
     Approaches
    -0.57
    Approach
    -0.56
    POSITIVE LOGITS
     address
    4.56
     Address
    4.22
    address
    4.16
     ADDRESS
    3.97
     addresses
    3.86
    Address
    3.83
     Addresses
    3.58
    ADDRESS
    3.56
     addressed
    3.47
     addressing
    3.38
    Activations Density 0.162%

    No Known Activations