© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 75233
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · 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
     more
    -1.11
     good
    -1.10
     there
    -1.09
     also
    -1.09
     this
    -1.09
     have
    -1.09
     you
    -1.08
     here
    -1.08
     that
    -1.08
     not
    -1.05
    POSITIVE LOGITS
     varandra
    0.66
     ögon
    0.58
     igång
    0.57
     igenom
    0.54
     barnen
    0.54
     vecka
    0.52
     händer
    0.52
     föruts
    0.52
     ifrån
    0.51
     länge
    0.49
    Activations Density 0.005%

    No Known Activations