© 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. 5-CLT-HP
    7. 92713
    Prev
    Next
    INDEX
    Explanations

    Code and technical tests

    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
    ValueStyle
    -1.00
     InputDecoration
    -0.75
    extAlignment
    -0.65
    出版年
    -0.64
    
    -0.63
     tomadas
    -0.61
    Enllaces
    -0.57
    Xna
    -0.57
     pinulongan
    -0.57
     tomada
    -0.56
    POSITIVE LOGITS
     Haupts
    0.59
     theirs
    0.55
     dimethyl
    0.55
     country
    0.54
    ræ
    0.54
     hers
    0.52
    etano
    0.51
    調
    0.51
     scre
    0.51
     Folge
    0.51
    Activations Density 0.000%

    No Known Activations