© 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. 94022
    Prev
    Next
    INDEX
    Explanations

    community

    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
    contentLoaded
    -0.64
     NSCoder
    -0.59
     հղումներ
    -0.59
    esModule
    -0.58
    XmlAccessType
    -0.58
    Portály
    -0.57
    rawtypes
    -0.56
    richTextPanel
    -0.53
    Personensuche
    -0.52
     âgées
    -0.50
    POSITIVE LOGITS
    <bos>
    0.54
     }^{[
    0.48
    QD
    0.47
    arsh
    0.47
    hru
    0.47
     AssemblyProduct
    0.47
    öny
    0.47
    ルク
    0.47
     Termin
    0.46
     Gib
    0.46
    Activations Density 0.001%

    No Known Activations