© 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. 1-CLT-HP
    7. 11630
    Prev
    Next
    INDEX
    Explanations

    code

    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
    OfMonth
    -0.57
     testify
    -0.53
    Източници
    -0.50
    ISupport
    -0.50
     bahay
    -0.49
    reporting
    -0.49
    NameInMap
    -0.48
    gouv
    -0.47
     Vaux
    -0.47
     Arque
    -0.47
    POSITIVE LOGITS
    ArrowToggle
    0.62
     recevez
    0.56
    createCanvas
    0.55
     propOrder
    0.53
    XmlAccessorType
    0.53
    исленность
    0.53
    writeHead
    0.52
    providedIn
    0.52
    nteral
    0.50
    dafx
    0.50
    Activations Density 1.450%

    No Known Activations