© 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. 6-RES-MATRYOSHKA-DC
    7. 534
    Prev
    Next
    INDEX
    Explanations

    the word "flow", often in the context of charts or industrial processes

    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
     fubject
    -0.99
     pleaſure
    -0.96
     Jefus
    -0.93
     myſelf
    -0.91
     McGu
    -0.90
     greateſt
    -0.90
     Majefty
    -0.88
     houſe
    -0.86
     Monfieur
    -0.86
     purpoſe
    -0.85
    POSITIVE LOGITS
     flow
    2.30
     Flow
    2.27
     flows
    2.19
     FLOW
    2.17
    flow
    2.14
    Flow
    2.11
     Flows
    2.03
    FLOW
    1.99
    flows
    1.91
    Flows
    1.84
    Activations Density 0.150%

    No Known Activations