© 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. 5-CLT-HP
    4. 96323
    Prev
    Next
    INDEX
    Explanations

    code and research

    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
     pneumoniae
    -0.79
    fjspx
    -0.74
    ItemBackground
    -0.69
    WebElementEntity
    -0.69
     Bioaccumulative
    -0.62
    OCCURRED
    -0.62
    UserScript
    -0.62
    GEBURTSDATUM
    -0.61
    يكب
    -0.60
     linkovi
    -0.58
    POSITIVE LOGITS
    hale
    0.58
    Autoritní
    0.56
     D
    0.48
     Rem
    0.48
    ]++;
    0.48
    ster
    0.48
    rem
    0.48
     ""));
    0.47
    e
    0.47
    jar
    0.47
    Activations Density 0.003%

    No Known Activations