© 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. 5-CLT-HP
    7. 96751
    Prev
    Next
    INDEX
    Explanations

    snippets of larger texts

    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
     vectorielle
    -0.50
    ainville
    -0.50
     Witte
    -0.50
     universelle
    -0.48
     suprême
    -0.47
     Italiana
    -0.47
     étrangères
    -0.47
     relatifs
    -0.46
     grecque
    -0.44
     nationales
    -0.44
    POSITIVE LOGITS
     initComponents
    0.89
    NameInMap
    0.88
    tagHelperRunner
    0.85
    dafx
    0.77
     Audiodateien
    0.74
     Roskov
    0.73
    новниш
    0.71
    XmlAccessorType
    0.68
     nahilalakip
    0.68
    حياته
    0.68
    Activations Density 0.001%

    No Known Activations