© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 920
    Prev
    Next
    INDEX
    Explanations

    penetration, gmail

    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
    bose
    -0.49
    xb
    -0.49
     bones
    -0.47
    bones
    -0.45
    блу
    -0.45
    Da
    -0.45
    Dore
    -0.44
     Dreyfus
    -0.44
    cor
    -0.44
    bon
    -0.44
    POSITIVE LOGITS
    таратура
    0.84
    Chham
    0.82
    sizeCache
    0.81
     testers
    0.75
     "..\..\
    0.68
    PreferredItem
    0.68
    RegressionTest
    0.68
     tester
    0.67
     Tester
    0.67
     PublicKey
    0.65
    Activations Density 0.002%

    No Known Activations