© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 296
    Prev
    Next
    INDEX
    Explanations

    cardiovascular

    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
     uova
    -0.56
     secos
    -0.53
     oeufs
    -0.52
     للمعارف
    -0.48
     igång
    -0.47
    ForValue
    -0.47
    нца
    -0.46
     InputDecoration
    -0.45
    bus
    -0.45
     uovo
    -0.45
    POSITIVE LOGITS
     تضيفلها
    0.57
    DockStyle
    0.54
    enumi
    0.54
    kheim
    0.53
    COUVER
    0.52
    jsonwebtoken
    0.52
    citep
    0.51
    RenderAtEndOf
    0.49
    Diweddarwch
    0.49
    Portale
    0.49
    Activations Density 0.003%

    No Known Activations