© 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. 1-CLT-HP
    7. 15342
    Prev
    Next
    INDEX
    Explanations

    physics

    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
     gravity
    -1.20
    gravity
    -0.94
     Gravity
    -0.71
    Gravity
    -0.69
     esternos
    -0.69
     GRAV
    -0.63
    GRAV
    -0.58
     gravedad
    -0.53
     gravitational
    -0.53
     vision
    -0.52
    POSITIVE LOGITS
     indisponible
    0.73
    TestingModule
    0.72
    GEBURTSDATUM
    0.72
    webElementXpaths
    0.65
     يتيمه
    0.63
    SharedCtor
    0.63
     eccell
    0.61
    UserScript
    0.60
    tanleria
    0.60
    :✨
    0.57
    Activations Density 0.009%

    No Known Activations