© 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. 96650
    Prev
    Next
    INDEX
    Explanations

    Units of measurement

    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
    fillType
    -0.84
     linkovi
    -0.76
    +#+#
    -0.75
    انيف
    -0.74
     snippetHide
    -0.73
     doInBackground
    -0.73
    mybatisplus
    -0.71
     مشين
    -0.70
    GEBURTSDATUM
    -0.69
    Portail
    -0.68
    POSITIVE LOGITS
     that
    0.68
     neutre
    0.54
     étranger
    0.52
     большие
    0.51
     vectorielles
    0.51
     larger
    0.50
     fréquent
    0.50
    ững
    0.48
     automatiques
    0.47
     supérieures
    0.47
    Activations Density 0.004%

    No Known Activations