© 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. 20-CLT-HP
    7. 76905
    Prev
    Next
    INDEX
    Explanations

    Code and programming errors

    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
     '\\;'
    -0.72
    WriteTagHelper
    -0.64
    aarrggbb
    -0.64
     beginnetje
    -0.56
    ometrica
    -0.56
     protoimpl
    -0.54
    sslich
    -0.54
    ₂+
    -0.52
    Xna
    -0.51
     Вікі
    -0.51
    POSITIVE LOGITS
    endphp
    0.62
    setupUi
    0.61
    TargetException
    0.51
     food
    0.50
    ActionPerformed
    0.49
    WithIOException
    0.49
     sin
    0.45
    addGap
    0.45
    trze
    0.45
     smelling
    0.44
    Activations Density 0.004%

    No Known Activations