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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4766
    Prev
    Next
    INDEX
    Explanations

    atmospheric

    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
     saurait
    -0.65
    InputTagHelper
    -0.63
     خارجية
    -0.63
     répondit
    -0.59
     חיצוניים
    -0.57
    mantec
    -0.56
     fotográfica
    -0.56
     continúas
    -0.56
     estimés
    -0.56
    nodoc
    -0.55
    POSITIVE LOGITS
     pressure
    0.75
    pressure
    0.54
    UserScript
    0.52
    toMatch
    0.49
    ClientSize
    0.49
     dese
    0.46
     air
    0.45
    PRESS
    0.45
     PRESSURE
    0.44
    圧
    0.44
    Activations Density 0.001%

    No Known Activations