© 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. 15117
    Prev
    Next
    INDEX
    Explanations

    "GP" and Beijing

    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
    GP
    -1.40
     GP
    -1.09
    gp
    -0.99
     gp
    -0.90
     GPs
    -0.74
     noires
    -0.64
     Syllabus
    -0.63
     insuffisamment
    -0.60
    settes
    -0.60
    Gp
    -0.59
    POSITIVE LOGITS
    ollectionView
    0.43
     Changes
    0.42
    indd
    0.42
    //
    0.41
     Cam
    0.41
     heapq
    0.41
    IsMutable
    0.40
     Arche
    0.40
    معلومات
    0.40
     Sprung
    0.39
    Activations Density 0.010%

    No Known Activations