© 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. 1742
    Prev
    Next
    INDEX
    Explanations

    your

    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
     the
    -0.66
    脚注の使い方
    -0.64
    šinou
    -0.55
     you
    -0.53
    akteur
    -0.48
     your
    -0.47
    hoots
    -0.47
     Tine
    -0.46
    olge
    -0.46
    หมือน
    -0.45
    POSITIVE LOGITS
    unknownFields
    0.63
    JspWriter
    0.59
    matter
    0.56
    Rhestr
    0.56
    Matter
    0.54
     modelAndView
    0.52
    XDECREF
    0.50
    JMenuBar
    0.50
     שוליים
    0.49
     nakalista
    0.49
    Activations Density 0.006%

    No Known Activations