© 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. 4043
    Prev
    Next
    INDEX
    Explanations

    the

    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
    richTextPanel
    -0.70
     estekak
    -0.65
     CreateTagHelper
    -0.63
    SharedDtor
    -0.62
    WithIOException
    -0.60
    Personendaten
    -0.59
    ⓧ
    -0.56
     propTypes
    -0.55
    migrationBuilder
    -0.55
    torie
    -0.54
    POSITIVE LOGITS
     great
    0.63
    group
    0.57
     group
    0.57
     cdti
    0.55
     so
    0.55
    framework
    0.55
     gruppe
    0.52
     ill
    0.52
     entourage
    0.52
    TextAlignment
    0.51
    Activations Density 0.005%

    No Known Activations