© 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. 4-CLT-HP
    4. 4875
    Prev
    Next
    INDEX
    Explanations

    Code and markup languages

    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
    __':
    
    -0.68
     celebration
    -0.60
    newswire
    -0.57
    SequentialGroup
    -0.56
     revanche
    -0.56
    inerja
    -0.56
     He
    -0.55
     missions
    -0.54
    holiday
    -0.54
     thanks
    -0.52
    POSITIVE LOGITS
     Paglinawan
    0.62
    retts
    0.57
    MigrationBuilder
    0.53
     Condado
    0.47
    awtextra
    0.47
    はじめに
    0.47
    Born
    0.46
    For
    0.44
    BrowserModule
    0.44
    On
    0.44
    Activations Density 0.001%

    No Known Activations