© 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. 4-CLT-HP
    7. 4889
    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
     the
    -0.66
    medriver
    -0.65
     Holidays
    -0.50
     Judaism
    -0.50
     viruses
    -0.50
     triangles
    -0.50
     holidays
    -0.49
     shells
    -0.49
     hormones
    -0.48
    rophoresis
    -0.48
    POSITIVE LOGITS
     发表于
    0.65
    الحياه
    0.62
    \{\\
    0.57
     Normdatei
    0.57
    stylers
    0.56
     للاسماء
    0.56
    ệnh
    0.55
    webElement
    0.54
    RUnlock
    0.53
    encodeWith
    0.52
    Activations Density 0.005%

    No Known Activations