© 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. 5-CLT-HP
    7. 4236
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     marins
    -0.63
     métallique
    -0.57
     intérieure
    -0.56
    Jegyzetek
    -0.56
    umumkan
    -0.56
     russes
    -0.54
     plastiques
    -0.52
     WIND
    -0.51
     خارجية
    -0.51
     expéri
    -0.51
    POSITIVE LOGITS
     المعيارى
    0.64
    InputBorder
    0.63
     оригіналу
    0.62
     noDo
    0.61
     jScrollPane
    0.58
     initComponents
    0.56
    Hills
    0.56
    anguages
    0.55
     Hills
    0.55
     صوتيه
    0.55
    Activations Density 0.000%

    No Known Activations