© 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. 91521
    Prev
    Next
    INDEX
    Explanations

    got

    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
     الحره
    -0.94
    fjspx
    -0.88
    IUrlHelper
    -0.82
    الحياه
    -0.79
     resourceCulture
    -0.77
    GEBURTSDATUM
    -0.74
    expandindo
    -0.72
    instancetype
    -0.71
     Económica
    -0.69
    Sucesor
    -0.69
    POSITIVE LOGITS
     clearly
    0.48
     generally
    0.45
    ByVersion
    0.45
     tend
    0.44
     OR
    0.43
     whether
    0.43
    NOPQRST
    0.43
     question
    0.41
     prefer
    0.41
    mozilla
    0.41
    Activations Density 0.005%

    No Known Activations