© 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. 0-CLT-HP
    4. 92578
    Prev
    Next
    INDEX
    Explanations

    Contin

    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
     costs
    -1.09
     itſelf
    -0.98
     ſche
    -0.93
     ſtate
    -0.92
     pleaſure
    -0.88
     Reſ
    -0.87
    costs
    -0.84
     houſe
    -0.84
    ſelf
    -0.84
     COSTS
    -0.83
    POSITIVE LOGITS
     بيها
    0.62
     kasarigan
    0.60
    RegistryLite
    0.59
    BeginContext
    0.58
    RegressionTest
    0.58
    KELEY
    0.53
    __*/
    0.51
    DockStyle
    0.51
    dailymail
    0.50
    CloseOperation
    0.49
    Activations Density 1.164%

    No Known Activations