© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3475
    Prev
    Next
    INDEX
    Explanations

    medicine/science

    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
    ftagPool
    -0.66
     EconPapers
    -0.59
    tablir
    -0.59
     referrerpolicy
    -0.57
    JspWriter
    -0.56
     enlaces
    -0.55
     gjen
    -0.54
    newtheorem
    -0.53
     slutt
    -0.53
     aikaa
    -0.52
    POSITIVE LOGITS
    escape
    0.49
    جغرافيا
    0.49
     stri
    0.47
    SerializedSize
    0.47
    ugs
    0.47
    fromnode
    0.47
     Spar
    0.46
    Cordial
    0.46
    lightbox
    0.46
     onOptions
    0.45
    Activations Density 0.007%

    No Known Activations