© 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. 1-CLT-HP
    7. 11922
    Prev
    Next
    INDEX
    Explanations

    ke

    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
    хьтан
    -0.85
     незавершена
    -0.66
     мәкал
    -0.65
     Roskov
    -0.63
    IntoConstraints
    -0.62
    AddTagHelper
    -0.61
     <=",
    -0.61
    SBATCH
    -0.61
    Datuak
    -0.59
    AnimationsModule
    -0.59
    POSITIVE LOGITS
     stat
    0.60
     Stat
    0.56
    acyj
    0.50
     Trade
    0.48
    jeta
    0.48
     Fair
    0.47
     Var
    0.46
     BoxFit
    0.46
    yip
    0.46
     }}</
    0.44
    Activations Density 0.020%

    No Known Activations