© 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. 95219
    Prev
    Next
    INDEX
    Explanations

    people and animals

    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
     cherchés
    -1.17
     themselves
    -1.02
    GEBURTSDATUM
    -1.00
    OGND
    -0.97
     تضيفلها
    -0.95
     themſelves
    -0.93
    themselves
    -0.89
     autorytatywna
    -0.82
    InputBorder
    -0.82
    
    -0.82
    POSITIVE LOGITS
    .
    0.59
     épaules
    0.58
    liana
    0.51
     I
    0.51
    ,
    0.50
    getreten
    0.49
    dje
    0.47
     côtés
    0.45
     lèvres
    0.45
     **
    0.43
    Activations Density 0.075%

    No Known Activations