© 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. 91340
    Prev
    Next
    INDEX
    Explanations

    images and colors

    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
    ITERATURE
    -0.54
    ConverterFactory
    -0.52
    halle
    -0.50
    ślę
    -0.50
    brainly
    -0.48
     Audiodateien
    -0.47
     whiteColor
    -0.47
    xique
    -0.47
    SystemColors
    -0.47
    Màu
    -0.47
    POSITIVE LOGITS
     continúas
    0.73
    TintMode
    0.65
    sidemargin
    0.61
    rrggbb
    0.58
     nahilalakip
    0.58
     considérons
    0.56
     تضيفلها
    0.54
    tagHelperRunner
    0.54
    httphttps
    0.52
    MessageWindow
    0.49
    Activations Density 0.001%

    No Known Activations