© 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. 43767
    Prev
    Next
    INDEX
    Explanations

    present

    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
    +#+#
    -1.08
     CreateTagHelper
    -0.90
    writeFieldEnd
    -0.87
     "..\..\..\
    -0.86
    adaptiveStyles
    -0.85
    tagHelperRunner
    -0.85
    ArrowToggle
    -0.83
    RenderAtEndOf
    -0.83
     propOrder
    -0.82
    Datuak
    -0.81
    POSITIVE LOGITS
    day
    0.63
    er
    0.60
     discussions
    0.58
    การณ์
    0.56
    个
    0.56
    t
    0.56
     discussion
    0.53
     day
    0.50
     times
    0.50
     these
    0.47
    Activations Density 0.108%

    No Known Activations