© 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. 91478
    Prev
    Next
    INDEX
    Explanations

    being superseded/replaced

    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
     doInBackground
    -0.60
     non
    -0.54
    atively
    -0.54
    Спољашње
    -0.52
     Non
    -0.52
     насељу
    -0.51
    ases
    -0.49
    UnusedPrivate
    -0.48
    ASES
    -0.48
    انيف
    -0.48
    POSITIVE LOGITS
    URLException
    0.73
     חיצוניים
    0.70
    исленность
    0.69
    :✨
    0.58
    ivasan
    0.57
    yntaxException
    0.57
    يكب
    0.56
    ArrowToggle
    0.56
    sizeCache
    0.56
    msgTypes
    0.54
    Activations Density 0.004%

    No Known Activations