© 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. 1-CLT-HP
    7. 15208
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    hara
    -1.61
    Hara
    -0.73
    ihara
    -0.71
     hara
    -0.64
     Hara
    -0.59
    er
    -0.52
     Henderson
    -0.49
    cz
    -0.48
    sh
    -0.48
    قبل
    -0.46
    POSITIVE LOGITS
     estekak
    0.94
     ProtoMessage
    0.90
     CreateTagHelper
    0.83
    aarrggbb
    0.81
    CloseOperation
    0.80
    клопе
    0.79
     propOrder
    0.78
    دانشنامهٔ
    0.77
     NavController
    0.76
    uxxxx
    0.75
    Activations Density 0.012%

    No Known Activations