© 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. 20-CLT-HP
    7. 75315
    Prev
    Next
    INDEX
    Explanations

    thing

    np_max-act-logits · 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
     سر
    -0.46
    Ad
    -0.45
    askar
    -0.44
    Pref
    -0.41
    webElementXpaths
    -0.40
     đáp
    -0.40
    Pop
    -0.40
     soci
    -0.40
     Ad
    -0.39
    Ớ
    -0.39
    POSITIVE LOGITS
     Thing
    1.20
    Thing
    1.15
     thing
    1.15
     THING
    1.14
    thing
    1.13
     Things
    1.09
    THING
    1.09
    Things
    1.05
    things
    1.04
    THINGS
    1.04
    Activations Density 0.001%

    No Known Activations