© 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. 3-RES-MATRYOSHKA-DC
    7. 2272
    Prev
    Next
    INDEX
    Explanations

    code relating to the transmission of data

    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
    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
     Majefty
    -0.77
     themſelves
    -0.76
     myſelf
    -0.76
     faſt
    -0.74
     ſeveral
    -0.74
     ſuch
    -0.73
     thermoc
    -0.73
     iſt
    -0.72
     leaſt
    -0.72
    GTCX
    -0.71
    POSITIVE LOGITS
    tx
    1.45
     tx
    1.23
    rx
    1.13
    TX
    1.08
    RX
    1.04
     Tx
    1.04
    Tx
    1.02
     rx
    1.02
     RX
    0.91
     TX
    0.90
    Activations Density 0.051%

    No Known Activations