© 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. 20-CLT-HP
    4. 74766
    Prev
    Next
    INDEX
    Explanations

    Names and organizations

    np_max-act-logits · 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
     estekak
    -0.60
    SerializedSize
    -0.54
    Round
    -0.54
    原始内容存档于
    -0.52
    ThroughAttribute
    -0.48
    RegressionTest
    -0.46
     Round
    -0.46
    state
    -0.46
    Hear
    -0.45
    front
    -0.45
    POSITIVE LOGITS
    AndEndTag
    0.69
    Földrajz
    0.57
     CWE
    0.57
     internetowa
    0.55
     Administrativna
    0.54
    Kaip
    0.54
    Reprints
    0.54
     nahilalakip
    0.51
    graphies
    0.51
     Bogor
    0.51
    Activations Density 0.003%

    No Known Activations