© 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. 98122
    Prev
    Next
    INDEX
    Explanations

    physical 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
    ressible
    -0.57
     onOptions
    -0.43
     chi̍t
    -0.43
    gazette
    -0.43
    Datuak
    -0.42
    ToPoint
    -0.42
     dagegen
    -0.42
    eip
    -0.41
    ofday
    -0.41
    ByUser
    -0.41
    POSITIVE LOGITS
     for
    0.88
     arşivlendi
    0.72
     okuyayım
    0.63
    CppMethod
    0.62
     متعلقه
    0.61
    └──
    0.59
     roulant
    0.57
    tagHelper
    0.57
    AccessorTable
    0.57
     pymongo
    0.56
    Activations Density 0.002%

    No Known Activations