© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 36
    Prev
    Next
    INDEX
    Explanations

    Code snippets and fragments

    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
     оригіналу
    -0.78
     betweenstory
    -0.73
    SourceChecksum
    -0.64
     Paglinawan
    -0.60
     kaarangay
    -0.60
    èdia
    -0.54
     ivelany
    -0.54
    الإنجليزية
    -0.53
     Мексичка
    -0.53
    AlterField
    -0.52
    POSITIVE LOGITS
     MonoBehaviour
    0.71
    sopp
    0.58
    viewtopic
    0.57
     Cap
    0.51
    ca
    0.50
    วา
    0.49
    spf
    0.47
    cca
    0.47
     Popup
    0.46
    BUF
    0.46
    Activations Density 0.000%

    No Known Activations