© 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. 2789
    Prev
    Next
    INDEX
    Explanations

    Proper nouns/titles

    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
    InputBorder
    -0.69
     Bunk
    -0.52
    BoxShadow
    -0.51
    MENAFN
    -0.50
     dirig
    -0.48
     Comet
    -0.47
     PopupWindow
    -0.46
    비
    -0.46
    はじめに
    -0.46
     通販
    -0.45
    POSITIVE LOGITS
     fermés
    0.56
    onAttach
    0.56
    ViewImports
    0.55
     Italijani
    0.55
     intStringLen
    0.54
    contentLoaded
    0.54
    <?
    0.53
     expériment
    0.52
    šanai
    0.52
     NUKAT
    0.51
    Activations Density 0.000%

    No Known Activations