© 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. 97205
    Prev
    Next
    INDEX
    Explanations

    connecting words

    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
     further
    -0.51
     inso
    -0.49
     another
    -0.47
    Another
    -0.46
     rendez
    -0.45
     sam
    -0.45
    mys
    -0.44
     entre
    -0.43
     Invis
    -0.43
     inf
    -0.43
    POSITIVE LOGITS
    TagMode
    0.86
     jScrollPane
    0.85
     protoimpl
    0.81
    DockStyle
    0.79
    AddTagHelper
    0.79
     épaules
    0.75
     jLabel
    0.74
    MigrationBuilder
    0.74
     Roskov
    0.73
     wikipagina
    0.73
    Activations Density 0.002%

    No Known Activations