© 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. 0-CLT-HP
    7. 93529
    Prev
    Next
    INDEX
    Explanations

    leadership, news

    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
    Leaders
    -0.77
     Leaders
    -0.75
     leaders
    -0.70
    itis
    -0.68
    leaders
    -0.65
     stable
    -0.63
    ire
    -0.61
    enge
    -0.60
    inge
    -0.53
    Stable
    -0.52
    POSITIVE LOGITS
     Theſe
    0.75
     يتيمه
    0.69
    ftagPool
    0.68
     autorytatywna
    0.67
     Réponses
    0.61
     MainAxisSize
    0.58
     Infórmanos
    0.56
    AddTagHelper
    0.55
     חיצוניים
    0.55
     betweenstory
    0.55
    Activations Density 0.053%

    No Known Activations