© 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. 10482
    Prev
    Next
    INDEX
    Explanations

    Real estate development

    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
    ^(@)
    -0.72
     Exacts
    -0.66
    новништво
    -0.65
    ؤلاء
    -0.63
    ajuato
    -0.63
     rectification
    -0.63
    forKey
    -0.62
    Clik
    -0.61
    ]<<"
    -0.60
     Epist
    -0.60
    POSITIVE LOGITS
    LookAnd
    0.52
    hilt
    0.51
    
    0.50
    ilt
    0.49
    GOTREF
    0.47
    MIDDLEWARE
    0.47
     оригіналу
    0.44
    stdc
    0.44
     Se
    0.43
     penjualan
    0.42
    Activations Density 0.054%

    No Known Activations