© 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. 2-RES-MATRYOSHKA-DC
    7. 5928
    Prev
    Next
    INDEX
    Explanations

    instances of the term "flow" in different contexts

    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
    Flu
    -1.71
     Flu
    -1.64
    flu
    -1.63
     FL
    -1.54
     Fl
    -1.46
     FLU
    -1.44
     flu
    -1.39
    Fl
    -1.37
     fl
    -1.35
    FL
    -1.34
    POSITIVE LOGITS
     flow
    1.89
     Flow
    1.70
    flow
    1.59
    Flow
    1.52
     FLOW
    1.27
     flows
    1.21
     Flows
    1.02
     flowed
    0.95
    FLOW
    0.91
    Flows
    0.90
    Activations Density 0.018%

    No Known Activations