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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 350
    Prev
    Next
    INDEX
    Explanations

    healthcare systems

    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
    styleable
    -0.65
    <bos>
    -0.60
    esterday
    -0.55
    Matériel
    -0.54
     Sociales
    -0.54
    monials
    -0.53
    ayer
    -0.53
     spira
    -0.52
     ampoule
    -0.52
    ESTIC
    -0.50
    POSITIVE LOGITS
     care
    0.68
    bootstrapcdn
    0.58
     jspb
    0.56
    ViewById
    0.56
     Care
    0.56
     cares
    0.51
    setViewportView
    0.50
     cuidado
    0.50
     Мексичка
    0.50
    posedge
    0.49
    Activations Density 0.044%

    No Known Activations