© 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. 4-CLT-HP
    7. 1034
    Prev
    Next
    INDEX
    Explanations

    bet

    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
    fjspx
    -0.59
    참고
    -0.52
    قبال
    -0.48
     Siam
    -0.47
     Grom
    -0.46
    id
    -0.45
     kali
    -0.45
    sanity
    -0.45
     impor
    -0.45
    ционер
    -0.45
    POSITIVE LOGITS
    ########.
    0.58
    WriteTagHelper
    0.56
    ValueGeneration
    0.55
    Clik
    0.55
    ponses
    0.54
    Helmut
    0.52
    MeasureSpec
    0.50
    brainly
    0.50
    RegressionTest
    0.50
    hesda
    0.50
    Activations Density 0.012%

    No Known Activations