© 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. 11489
    Prev
    Next
    INDEX
    Explanations

    ils

    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
     ghost
    -0.69
    IANGLES
    -0.68
    SequentialGroup
    -0.67
     Ghost
    -0.64
     مشين
    -0.63
     Ghosts
    -0.63
    Ghosts
    -0.61
     kasarigan
    -0.60
    Gén
    -0.59
    ghost
    -0.59
    POSITIVE LOGITS
     themſelves
    0.55
     rús
    0.55
     jurí
    0.53
     diputados
    0.52
    Razer
    0.51
     clínicas
    0.50
     Eſ
    0.49
     fondament
    0.48
    Navigation
    0.48
     clínicos
    0.48
    Activations Density 0.018%

    No Known Activations