© 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. 3222
    Prev
    Next
    INDEX
    Explanations

    stap

    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
    #+#
    -0.84
    ///</
    -0.81
     ویکی‌پدیا
    -0.81
    UnusedPrivate
    -0.81
     initComponents
    -0.80
     Monfieur
    -0.79
    MessageTagHelper
    -0.79
     Efq
    -0.77
    exitRule
    -0.77
    fjspx
    -0.77
    POSITIVE LOGITS
    me
    0.46
    তে
    0.45
    ет
    0.41
    ซ์
    0.40
    ह
    0.38
     pneumoniae
    0.38
    x
    0.36
     }_{
    0.36
    يره
    0.35
    DNA
    0.35
    Activations Density 0.013%

    No Known Activations