© 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. 4-CLT-HP
    7. 1670
    Prev
    Next
    INDEX
    Explanations

    see

    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
    出版年
    -1.09
     EconPapers
    -1.05
     GenerationType
    -1.03
     мәкалә
    -1.02
    WebVitals
    -0.97
     jScrollPane
    -0.95
     صوتيه
    -0.95
    Према
    -0.94
    طلحات
    -0.93
    WriteTagHelper
    -0.92
    POSITIVE LOGITS
     know
    0.50
    ;
    0.44
     חיצוניים
    0.43
    :
    0.43
     for
    0.41
     have
    0.41
     finally
    0.40
    Finally
    0.39
    .
    0.39
    !
    0.38
    Activations Density 0.004%

    No Known Activations