© 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. 4062
    Prev
    Next
    INDEX
    Explanations

    people

    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
    -0.93
    SpringBootTest
    -0.81
     pinulongan
    -0.81
    FormTagHelper
    -0.81
    Personensuche
    -0.77
    igshid
    -0.75
    transQ
    -0.74
    sizeCache
    -0.73
    contentLoaded
    -0.72
    setDo
    -0.71
    POSITIVE LOGITS
     might
    0.83
     may
    0.76
     can
    0.72
     want
    0.71
     find
    0.71
     are
    0.71
     have
    0.70
     would
    0.67
     consider
    0.65
     think
    0.64
    Activations Density 0.003%

    No Known Activations