© 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. 1-CLT-HP
    7. 13782
    Prev
    Next
    INDEX
    Explanations

    using

    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
    MLLoader
    -0.61
    MessageTagHelper
    -0.56
    thalene
    -0.55
    AnchorStyles
    -0.53
    ետ
    -0.52
    esez
    -0.52
     purpose
    -0.50
    ฐ
    -0.50
    AutoresizingMask
    -0.50
    ulatus
    -0.49
    POSITIVE LOGITS
    ViewFeatures
    0.64
    ValueStyle
    0.60
    __((
    0.55
    tvguidetime
    0.54
     ComVisible
    0.54
    unknownFields
    0.54
     suspic
    0.52
    MENAFN
    0.52
    endwhile
    0.51
    :]:
    0.50
    Activations Density 0.005%

    No Known Activations