© 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. 243
    Prev
    Next
    INDEX
    Explanations

    seh

    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
    UnusedPrivate
    -0.50
     Bio
    -0.49
     Valdez
    -0.49
    DebuggerNonUser
    -0.48
    новниш
    -0.47
    Bio
    -0.47
    oustics
    -0.45
    ']>
    -0.44
    pgsql
    -0.44
    ']='
    -0.43
    POSITIVE LOGITS
    PreferredItem
    0.70
     Shiba
    0.54
    setupUi
    0.54
    WRP
    0.54
    olish
    0.52
    modelBuilder
    0.52
     Secondary
    0.52
    AndEndTag
    0.52
    verwijspagina
    0.50
    存于互联网档案馆
    0.50
    Activations Density 0.001%

    No Known Activations