© 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. 1-CLT-HP
    7. 12435
    Prev
    Next
    INDEX
    Explanations

    thrombus/blood clots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cro
    -0.92
     propOrder
    -0.91
    crop
    -0.90
    crops
    -0.83
     crops
    -0.81
     crop
    -0.77
     AssemblyCulture
    -0.77
    NameInMap
    -0.76
    cropping
    -0.74
    CRO
    -0.73
    POSITIVE LOGITS
    OLIS
    0.57
    ure
    0.49
    olis
    0.47
     Stich
    0.44
     Ready
    0.42
    Thesis
    0.41
    hesis
    0.41
    TURE
    0.41
    als
    0.40
    arf
    0.40
    Activations Density 0.155%

    No Known Activations