© 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. 2088
    Prev
    Next
    INDEX
    Explanations

    of

    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
    StoryboardSegue
    -0.60
    enumi
    -0.60
     Schaefer
    -0.57
     RSSSF
    -0.57
    becker
    -0.56
    Activités
    -0.55
    AccessorTable
    -0.55
    ocene
    -0.54
     Days
    -0.54
    BeginInit
    -0.53
    POSITIVE LOGITS
    war
    0.68
     war
    0.66
     onBind
    0.54
    wart
    0.53
    warf
    0.51
    HandlerContext
    0.51
     onAnimation
    0.50
    WAR
    0.49
    RenderAtEndOf
    0.47
    WaitGroup
    0.46
    Activations Density 0.001%

    No Known Activations