© 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. 0-CLT-HP
    7. 42807
    Prev
    Next
    INDEX
    Explanations

    measurements or calculations

    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
     autorytatywna
    -0.64
    phazard
    -0.57
    ByUserId
    -0.56
     تضيفلها
    -0.54
    universe
    -0.52
    Loud
    -0.52
    ült
    -0.52
    nucleus
    -0.52
     Bunga
    -0.52
     vš
    -0.51
    POSITIVE LOGITS
     GenerationType
    0.71
    ArrowToggle
    0.59
     насељу
    0.59
     للمعارف
    0.58
    djangoproject
    0.57
     Italijanski
    0.51
    ագրություններ
    0.49
     '\\;'
    0.49
     Obrador
    0.49
    تفصیلات
    0.48
    Activations Density 0.362%

    No Known Activations