© 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. 14595
    Prev
    Next
    INDEX
    Explanations

    Dr

    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
     dr
    -0.60
    dr
    -0.59
    }*/
    -0.52
    出版年
    -0.50
    Dr
    -0.50
     Dr
    -0.49
    ")]
    -0.48
    "),
    -0.47
    moveToFirst
    -0.46
     physicians
    -0.45
    POSITIVE LOGITS
     تضيفلها
    0.69
     saites
    0.62
    webElementXpaths
    0.60
    
    0.55
    tisgarh
    0.50
    endphp
    0.48
     CiNii
    0.48
     Familienname
    0.48
    roek
    0.47
    <caption>
    0.47
    Activations Density 0.003%

    No Known Activations