© 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. 1899
    Prev
    Next
    INDEX
    Explanations

    Truth

    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
     truth
    -1.37
    ating
    -1.27
     Truth
    -1.09
    truth
    -1.09
     TRUTH
    -1.06
    Truth
    -1.00
    ATING
    -0.97
     verdad
    -0.84
     Wahrheit
    -0.80
     vérit
    -0.80
    POSITIVE LOGITS
    fulness
    0.60
     actionPerformed
    0.60
     виправивши
    0.56
     Roskov
    0.56
    AndroidJUnit
    0.53
    fully
    0.53
    peka
    0.52
    例句
    0.52
     arbitrage
    0.52
    math
    0.51
    Activations Density 0.043%

    No Known Activations