© 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. 20-CLT-HP
    4. 75175
    Prev
    Next
    INDEX
    Explanations

    research and names

    np_max-act-logits · 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
    InstrumentedTest
    -0.70
     Italijanski
    -0.68
     Numerade
    -0.66
     tartalomajánló
    -0.63
    #+#
    -0.63
    PMailer
    -0.62
     Италијани
    -0.62
    tsen
    -0.62
    Abitanti
    -0.59
    مصادر
    -0.58
    POSITIVE LOGITS
    CodeAttribute
    0.54
    æg
    0.50
    giat
    0.48
    ky
    0.44
    ägg
    0.43
     repuesto
    0.42
    ansu
    0.41
    Eg
    0.41
     cuivre
    0.41
    lagi
    0.41
    Activations Density 0.000%

    No Known Activations