© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15950
    Prev
    Next
    INDEX
    Explanations

    best

    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
    Gardner
    -0.52
     Gardner
    -0.49
     árvores
    -0.47
    ंदीखरीदारी
    -0.47
     stack
    -0.45
     vegetales
    -0.45
     Stor
    -0.45
    water
    -0.45
     Wolver
    -0.45
    ureka
    -0.44
    POSITIVE LOGITS
    IsContent
    0.69
     outcomes
    0.68
     Paglinawan
    0.66
    Personendaten
    0.63
     outcome
    0.60
     Outcomes
    0.60
    CppMethod
    0.60
    انيف
    0.57
    InjectAttribute
    0.57
    outcomes
    0.57
    Activations Density 0.072%

    No Known Activations