© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14367
    Prev
    Next
    INDEX
    Explanations

    Ramsay

    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
     Canto
    -0.60
    ed
    -0.59
    Canto
    -0.58
    🏻
    -0.57
    ist
    -0.57
    
    -0.55
    z
    -0.51
    ary
    -0.50
    ic
    -0.50
    n
    -0.50
    POSITIVE LOGITS
    GEBURTSDATUM
    0.75
    पया
    0.64
    complexContent
    0.64
    mybatisplus
    0.63
    DIPSETTING
    0.63
    CppMethod
    0.61
     الرياضيه
    0.61
    netty
    0.60
    
    0.59
    mbor
    0.58
    Activations Density 0.129%

    No Known Activations