© 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. 5161
    Prev
    Next
    INDEX
    Explanations

    reach

    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
     محفوظة
    -0.83
     оригіналу
    -0.74
    دانشنامهٔ
    -0.71
    Hozzáférés
    -0.68
     disponibilités
    -0.65
     שוליים
    -0.65
     الاطلاع
    -0.64
    ImageContext
    -0.64
     EconPapers
    -0.63
    Билгалдахарш
    -0.63
    POSITIVE LOGITS
     wide
    0.55
    MongoClient
    0.54
    igshid
    0.52
     widely
    0.49
    afficheront
    0.48
     širo
    0.47
     يتيمه
    0.46
    groß
    0.46
    bodyParser
    0.42
    atrième
    0.42
    Activations Density 0.001%

    No Known Activations