© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97394
    Prev
    Next
    INDEX
    Explanations

    time units

    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
     Dess
    -0.51
     PMS
    -0.50
     continuará
    -0.50
     ASF
    -0.49
    ism
    -0.49
    CCB
    -0.48
     Thurman
    -0.47
     gelegen
    -0.47
    Rhestr
    -0.47
     Kiki
    -0.46
    POSITIVE LOGITS
    Diwedd
    0.61
     or
    0.57
     layui
    0.56
     initComponents
    0.55
    Personendaten
    0.54
    long
    0.53
     &___
    0.52
    发表于
    0.50
    NamedQueries
    0.49
    Expedia
    0.49
    Activations Density 0.002%

    No Known Activations