© 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. 20-CLT-HP
    7. 73665
    Prev
    Next
    INDEX
    Explanations

    actions and configurations

    np_max-act-logits · 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
    Personendaten
    -0.72
     Nacionales
    -0.54
     fatica
    -0.52
    Artic
    -0.51
    antaine
    -0.51
    junto
    -0.50
     pinulongan
    -0.49
     gene
    -0.49
    出去
    -0.48
    èdia
    -0.48
    POSITIVE LOGITS
     up
    1.09
     Up
    0.80
    up
    0.65
     UP
    0.64
    Up
    0.64
     تضيفلها
    0.63
    AddTagHelper
    0.60
     uo
    0.53
     ups
    0.53
    )))));
    0.52
    Activations Density 0.003%

    No Known Activations