© 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. 3399
    Prev
    Next
    INDEX
    Explanations

    particles and atoms

    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
     odeur
    -0.56
     of
    -0.47
    IUrlHelper
    -0.45
     maîtres
    -0.44
     réputation
    -0.44
     hjälpa
    -0.43
     Sixteenth
    -0.43
     faveur
    -0.41
     elfog
    -0.41
     équilibre
    -0.41
    POSITIVE LOGITS
     AssemblyCulture
    0.70
    évaluateur
    0.65
    .},
    0.63
     betweenstory
    0.63
    AddTagHelper
    0.63
    DrawerToggle
    0.60
    tonode
    0.58
    InSection
    0.57
    ukone
    0.57
    WindowConstants
    0.56
    Activations Density 0.001%

    No Known Activations