© 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. 0-CLT-HP
    7. 45452
    Prev
    Next
    INDEX
    Explanations

    prisoners

    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
    WriteAttribute
    -0.58
    lapsingToolbar
    -0.57
    ignite
    -0.51
    Πηγές
    -0.51
    platinum
    -0.50
    frauen
    -0.50
    champagne
    -0.49
    CPtr
    -0.49
     tweeted
    -0.49
    Gin
    -0.49
    POSITIVE LOGITS
    ConstraintMaker
    0.62
    endregion
    0.62
    PhysRev
    0.60
    DebuggerNonUser
    0.59
    تقاوى
    0.59
    мум
    0.58
    enguaje
    0.57
     iſt
    0.57
    mobileqq
    0.57
    嘧
    0.56
    Activations Density 0.094%

    No Known Activations