© 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. 1-CLT-HP
    4. 11705
    Prev
    Next
    INDEX
    Explanations

    Patents and presentations

    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
    CHM
    -0.50
    alakip
    -0.49
     interests
    -0.49
    ày
    -0.48
     fá
    -0.47
    kowym
    -0.47
     rés
    -0.46
     foot
    -0.45
    LEGGI
    -0.44
    脚注の使い方
    -0.44
    POSITIVE LOGITS
    AddTagHelper
    0.77
    
    0.61
     gynhyrchwyd
    0.60
    balleur
    0.59
    ilever
    0.57
    BagLayout
    0.57
    XtraEditors
    0.56
    Diweddarwch
    0.56
    jména
    0.55
    ArgsConstructor
    0.54
    Activations Density 0.017%

    No Known Activations