© 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. 3188
    Prev
    Next
    INDEX
    Explanations

    abortion

    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
     onOptions
    -0.49
     jScrollPane
    -0.48
    webpack
    -0.47
     Chance
    -0.46
    bufio
    -0.46
    Abitanti
    -0.45
    SupportActionBar
    -0.43
    두
    -0.43
    stretch
    -0.43
    жок
    -0.43
    POSITIVE LOGITS
    TagMode
    0.78
     rights
    0.63
    setVerticalGroup
    0.63
     nurseries
    0.57
    Koordinaten
    0.54
    oneofs
    0.53
     Zugang
    0.53
    |}{$
    0.53
     parut
    0.52
    ists
    0.52
    Activations Density 0.002%

    No Known Activations