© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2634
    Prev
    Next
    INDEX
    Explanations

    miscellaneous text

    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
    La
    -0.43
    менно
    -0.42
     reparti
    -0.40
     gradova
    -0.39
     La
    -0.39
    ContentAsync
    -0.38
    Met
    -0.37
    ring
    -0.37
    город
    -0.36
    ly
    -0.36
    POSITIVE LOGITS
     Chwiliwch
    0.89
    PreferredItem
    0.80
     tartalomajánló
    0.77
     XCTest
    0.70
    IntoConstraints
    0.69
     AssemblyCulture
    0.67
    تقاوى
    0.65
    цездатний
    0.64
     neutre
    0.62
    tvguidetime
    0.60
    Activations Density 0.113%

    No Known Activations