© 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. 3232
    Prev
    Next
    INDEX
    Explanations

    -

    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
     للاسماء
    -0.80
    andescent
    -0.62
     WaitForSeconds
    -0.61
    ceptre
    -0.59
    المكان
    -0.56
    tope
    -0.56
    tagext
    -0.56
    createView
    -0.56
    ramine
    -0.56
    virons
    -0.55
    POSITIVE LOGITS
    Vidite
    0.56
    ništ
    0.47
     Italijani
    0.47
    ยว
    0.46
     kasarigan
    0.46
     initComponents
    0.45
     ligiloj
    0.44
    횟
    0.42
    ="@+
    0.41
    出版年
    0.41
    Activations Density 0.001%

    No Known Activations