© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75712
    Prev
    Next
    INDEX
    Explanations

    technical/programming and names, basically

    np_max-act-logits · 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
    TagMode
    -0.76
    IntoConstraints
    -0.75
     noDo
    -0.73
     propOrder
    -0.72
    RegressionTest
    -0.71
    PerformLayout
    -0.58
    arraycopy
    -0.58
    titleMargin
    -0.58
    TargetException
    -0.57
     sẻ
    -0.57
    POSITIVE LOGITS
    InputBorder
    0.48
    Gale
    0.46
     Gale
    0.45
     Deb
    0.45
     Sally
    0.44
     BSP
    0.43
    TintMode
    0.42
    usters
    0.42
     kinetics
    0.42
     Ause
    0.42
    Activations Density 0.000%

    No Known Activations