© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4987
    Prev
    Next
    INDEX
    Explanations

    signals related to surface coating methods and their properties

    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
     flow
    -0.94
    flow
    -0.78
     Flow
    -0.76
     flows
    -0.74
    Flow
    -0.69
     flowed
    -0.63
    Flows
    -0.62
     flowing
    -0.61
    flowing
    -0.59
    iov
    -0.57
    POSITIVE LOGITS
    FL
    3.14
     FL
    2.94
    fl
    2.44
     Fl
    2.22
    Fl
    2.19
     fl
    2.03
    FLP
    1.58
     Fla
    1.48
    Fla
    1.47
    FLT
    1.46
    Activations Density 0.016%

    No Known Activations