© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75787
    Prev
    Next
    INDEX
    Explanations

    Code/technical snippets

    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
    <![
    -0.56
     ground
    -0.53
     Awak
    -0.52
    ียบ
    -0.50
    quea
    -0.49
    hic
    -0.48
    FormTagHelper
    -0.48
    PMailer
    -0.48
    ılı
    -0.47
     میلی
    -0.47
    POSITIVE LOGITS
    bcryptjs
    0.68
    richTextPanel
    0.67
    abstractmethod
    0.63
     Савезне
    0.58
    Personendaten
    0.56
    InputBorder
    0.54
    disposing
    0.52
    marshaller
    0.51
    __':
    0.51
    /*
    0.50
    Activations Density 0.000%

    No Known Activations