© 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. 5-CLT-HP
    4. 2501
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Oppen
    -0.54
    #+#
    -0.54
     surla
    -0.53
     تضيفلها
    -0.51
     Jove
    -0.50
    trzyma
    -0.50
     sourire
    -0.48
     asunder
    -0.48
    êtements
    -0.48
    timewa
    -0.47
    POSITIVE LOGITS
    InjectAttribute
    0.61
    __':
    
    0.59
    fillType
    0.56
    extAlignment
    0.55
     Reproduce
    0.50
     unknownFields
    0.47
    Jereo
    0.47
    contentLoaded
    0.47
     Island
    0.47
     imp
    0.47
    Activations Density 0.006%

    No Known Activations