© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13617
    Prev
    Next
    INDEX
    Explanations

    Contractions

    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
     réfugiés
    -0.62
     épu
    -0.61
    rrggbb
    -0.59
     bakgrund
    -0.58
     pauvres
    -0.58
     trânsito
    -0.58
     écl
    -0.56
     graisse
    -0.56
     réfugi
    -0.55
    utilisons
    -0.54
    POSITIVE LOGITS
     contextLoads
    0.68
    getSystemService
    0.62
     مرئيه
    0.61
    )";
    0.61
    Personendaten
    0.60
    posedge
    0.57
    
    0.57
     chains
    0.57
    AccessException
    0.56
     strtok
    0.54
    Activations Density 0.036%

    No Known Activations