© 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. 5-CLT-HP
    7. 2512
    Prev
    Next
    INDEX
    Explanations

    s

    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
     
    -0.43
     F
    -0.41
     ar
    -0.41
     ...
    -0.40
     R
    -0.40
    </strong>
    -0.39
     A
    -0.39
     x
    -0.38
     Al
    -0.38
    fromCharCode
    -0.37
    POSITIVE LOGITS
    Vidite
    0.90
     CreateTagHelper
    0.90
    enumii
    0.89
     Paglinawan
    0.89
    Datuak
    0.83
     myſelf
    0.83
    enumi
    0.81
    клопе
    0.80
     Theſe
    0.79
     bershka
    0.79
    Activations Density 0.002%

    No Known Activations