© 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. 75152
    Prev
    Next
    INDEX
    Explanations

    French words

    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
    <bos>
    -0.70
    λοι
    -0.34
    ρυ
    -0.34
    xFFFFFF
    -0.31
    ικα
    -0.31
    нен
    -0.31
    ff
    -0.30
    xffffffff
    -0.29
    出版年
    -0.29
    UMEN
    -0.29
    POSITIVE LOGITS
     supérieurs
    0.31
    ⓧ
    0.30
     démocr
    0.29
     automatiques
    0.29
     financières
    0.28
     normaux
    0.28
     fermés
    0.28
     supérieures
    0.27
     scolaires
    0.26
     complètes
    0.25
    Activations Density 0.003%

    No Known Activations