© 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. 4-CLT-HP
    4. 2804
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     nakalista
    -0.59
    most
    -0.52
    Most
    -0.52
     Most
    -0.52
     that
    -0.52
    hamdulillah
    -0.50
     tiap
    -0.50
    that
    -0.48
    DECREF
    -0.48
     fleste
    -0.47
    POSITIVE LOGITS
    fjspx
    0.72
     jScrollPane
    0.72
    ReusableCell
    0.71
     like
    0.71
    awtextra
    0.69
     CreateTagHelper
    0.68
     intStringLen
    0.65
    WebVitals
    0.63
     như
    0.63
    pertino
    0.63
    Activations Density 0.001%

    No Known Activations