© 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. 0-CLT-HP
    7. 94478
    Prev
    Next
    INDEX
    Explanations

    ForRow

    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
    addWidget
    -0.55
    #+#
    -0.53
    
    -0.53
    copyWith
    -0.51
    mybatisplus
    -0.51
     Орден
    -0.47
    コロ
    -0.44
    entibus
    -0.44
     tvb
    -0.44
    τί
    -0.43
    POSITIVE LOGITS
    writeFieldEnd
    0.77
     للمعارف
    0.72
    Bibliograf
    0.62
     nahilalakip
    0.60
    SourceChecksum
    0.60
    Carriera
    0.59
    Jereo
    0.59
    Datuak
    0.57
    تفصیلات
    0.57
     зру
    0.57
    Activations Density 1.944%

    No Known Activations