© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40127
    Prev
    Next
    INDEX
    Explanations

    feature

    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
     Feature
    -1.09
    Feature
    -1.07
    feature
    -1.04
     feature
    -1.00
     FEATURE
    -0.72
    FEATURE
    -0.67
    featured
    -0.60
     featured
    -0.60
     features
    -0.58
     Featured
    -0.57
    POSITIVE LOGITS
    zili
    0.60
    fulness
    0.58
    Demografia
    0.57
    emes
    0.56
     تضيفلها
    0.54
     Autorizaciones
    0.54
    onomy
    0.54
    ysen
    0.54
     Fus
    0.53
    ectomy
    0.53
    Activations Density 1.673%

    No Known Activations