© 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. 4920
    Prev
    Next
    INDEX
    Explanations

    million

    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
    ClientSize
    -0.53
    ajemen
    -0.52
    RegressionTest
    -0.52
    Geplaatst
    -0.52
    Bibliograf
    -0.51
    URERS
    -0.49
    енча
    -0.49
    TestTools
    -0.49
    Viited
    -0.49
    .",
    -0.49
    POSITIVE LOGITS
     arşivlendi
    0.53
     defaultstate
    0.52
    BufferException
    0.52
     onPress
    0.51
    ذن
    0.50
     Wicidata
    0.49
     specimens
    0.48
     المعيارى
    0.47
     Pina
    0.46
    ⓘ
    0.46
    Activations Density 0.003%

    No Known Activations