© 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. 0-CLT-HP
    4. 38351
    Prev
    Next
    INDEX
    Explanations

    chili

    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
    IntoConstraints
    -0.90
    ंदीखरीदारी
    -0.84
     للاسماء
    -0.82
     CreateTagHelper
    -0.79
     Paglinawan
    -0.79
    tagHelperRunner
    -0.77
    Personensuche
    -0.77
     nakalista
    -0.77
    mybatisplus
    -0.75
    AndEndTag
    -0.75
    POSITIVE LOGITS
    SerializeField
    0.61
    ally
    0.50
    laim
    0.49
     public
    0.48
    createCell
    0.46
    public
    0.44
    DrawerToggle
    0.44
    RESUMO
    0.44
     prek
    0.42
    moncler
    0.42
    Activations Density 1.438%

    No Known Activations