© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 2044
    Prev
    Next
    INDEX
    Explanations

    blood pressure

    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
     سكانية
    -0.59
    setupUi
    -0.56
    Slf
    -0.54
     baumwolle
    -0.54
     Efq
    -0.54
     flyknit
    -0.52
     itſelf
    -0.52
     Theſe
    -0.52
    </thead>
    -0.51
    Posté
    -0.51
    POSITIVE LOGITS
     تضيفلها
    0.68
     Vikipedi
    0.65
    togram
    0.63
    amoan
    0.58
    ConstraintMaker
    0.58
     ComVisible
    0.57
    Parcelize
    0.54
     متعلقه
    0.52
     dAtA
    0.52
     estómago
    0.49
    Activations Density 0.196%

    No Known Activations