© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1647
    Prev
    Next
    INDEX
    Explanations

    meteor

    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
     bait
    -0.74
    verwijspagina
    -0.72
    rungsseite
    -0.71
    thâu
    -0.71
    adaptiveStyles
    -0.69
     Aquarium
    -0.69
     '\\;'
    -0.68
    bait
    -0.68
     surla
    -0.67
    RetentionPolicy
    -0.67
    POSITIVE LOGITS
    ness
    0.56
    nya
    0.53
    ting
    0.52
    zon
    0.51
     animali
    0.50
    st
    0.49
    ve
    0.48
    sten
    0.47
    re
    0.47
    se
    0.47
    Activations Density 0.042%

    No Known Activations