© 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. 4-CLT-HP
    7. 1781
    Prev
    Next
    INDEX
    Explanations

    medical or religious practices

    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
    rungsseite
    -0.80
     practiced
    -0.78
     practised
    -0.77
     practice
    -0.73
     practicing
    -0.70
     practising
    -0.65
    таратура
    -0.65
     Мексичка
    -0.62
    المكان
    -0.62
     snippetHide
    -0.60
    POSITIVE LOGITS
    Rotated
    0.51
     Mysterious
    0.49
    redit
    0.49
     futility
    0.49
    underbrace
    0.48
     Violent
    0.48
     etapas
    0.47
     jos
    0.47
     köl
    0.46
     aank
    0.46
    Activations Density 0.005%

    No Known Activations