© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4675
    Prev
    Next
    INDEX
    Explanations

    reckoned

    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
     calendriers
    -0.75
    RectangleBorder
    -0.73
    DoubleQuotes
    -0.61
     оригіналу
    -0.58
     pinulongan
    -0.57
     محفوظة
    -0.56
    ClientRect
    -0.55
    IntoConstraints
    -0.53
    oas
    -0.52
     campagnes
    -0.51
    POSITIVE LOGITS
    ürme
    0.48
    NegativeButton
    0.48
     Elaine
    0.47
     Sharing
    0.46
     Bag
    0.46
     Scale
    0.46
     feedback
    0.45
     base
    0.44
     weakness
    0.44
     quite
    0.44
    Activations Density 0.001%

    No Known Activations