© 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. 94374
    Prev
    Next
    INDEX
    Explanations

    start of sentences/sections

    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
     betweenstory
    -0.63
     snippetHide
    -0.62
    ̈́
    -0.54
    LEARN
    -0.54
     دیکھیے
    -0.54
    astéro
    -0.53
     تضيفلها
    -0.52
     itſelf
    -0.50
    atég
    -0.49
     popoli
    -0.49
    POSITIVE LOGITS
     kasarigan
    0.63
    CloseOperation
    0.62
     Dutchman
    0.55
    سطس
    0.52
    lot
    0.52
     lot
    0.51
    Geplaatst
    0.50
    dehyde
    0.49
     surla
    0.49
     Frenchman
    0.48
    Activations Density 0.000%

    No Known Activations