© 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. 0-CLT-HP
    7. 43902
    Prev
    Next
    INDEX
    Explanations

    here

    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
     here
    -1.82
     aquí
    -1.42
     здесь
    -1.31
    here
    -1.28
    在这里
    -1.27
     ici
    -1.25
     disini
    -1.20
     aici
    -1.19
     هنا
    -1.16
     aqui
    -1.13
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.79
    ########.
    0.77
     Efq
    0.75
     Houſe
    0.75
    writeFieldEnd
    0.73
    PerformLayout
    0.71
     CURLOPT
    0.70
    UnusedPrivate
    0.69
    TestingModule
    0.68
    tagHelper
    0.68
    Activations Density 0.034%

    No Known Activations