© 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. 5-CLT-HP
    7. 3395
    Prev
    Next
    INDEX
    Explanations

    legal/references to people

    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
    RenderAtEndOf
    -0.66
    ,‎
    -0.60
     Inflate
    -0.58
    complexContent
    -0.58
     Alternatively
    -0.57
    ",{
    -0.57
     weights
    -0.57
    getWriter
    -0.55
    ışık
    -0.54
    publ
    -0.54
    POSITIVE LOGITS
    <bos>
    0.62
    хьтан
    0.47
    Chham
    0.46
    Див
    0.45
    rungsseite
    0.42
    FTFY
    0.41
    RTLR
    0.40
    RegressionTest
    0.39
     CreateTagHelper
    0.39
    Jeografia
    0.39
    Activations Density 0.011%

    No Known Activations