© 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. 305
    Prev
    Next
    INDEX
    Explanations

    references to the flow or movement of fluids or gases

    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
     Partridge
    -0.59
    lblNewLabel
    -0.56
     BoxFit
    -0.55
    UrlResolution
    -0.54
     eminence
    -0.52
    Sabah
    -0.52
     burying
    -0.52
     تضيفلها
    -0.51
     AssemblyTitle
    -0.50
     NER
    -0.50
    POSITIVE LOGITS
     flow
    4.59
     Flow
    4.34
    flow
    4.22
    Flow
    4.13
     FLOW
    3.92
     flows
    3.81
     Flows
    3.64
    FLOW
    3.53
    flows
    3.45
     flowed
    3.30
    Activations Density 0.847%

    No Known Activations