© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92101
    Prev
    Next
    INDEX
    Explanations

    publication-related text fragments

    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
     समीक्षक
    -0.57
     referenties
    -0.56
    LookAnd
    -0.52
     AssemblyCulture
    -0.48
    durch
    -0.46
    InputBorder
    -0.44
    RetentionPolicy
    -0.44
     independent
    -0.42
     eating
    -0.42
     unha
    -0.42
    POSITIVE LOGITS
    CONSIN
    0.58
    mazoo
    0.50
    sonian
    0.50
    NewUrlParser
    0.50
     afspraak
    0.50
    ंदीखरीदारी
    0.49
     verwacht
    0.49
    ,
    0.48
     tarik
    0.47
     Picchu
    0.46
    Activations Density 0.002%

    No Known Activations