© 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. 1-CLT-HP
    7. 9370
    Prev
    Next
    INDEX
    Explanations

    dust/particles

    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
    aarrggbb
    -0.63
    @[+][
    -0.57
    uyasha
    -0.53
    먼
    -0.46
    nocześnie
    -0.45
    heids
    -0.43
     dust
    -0.43
    uver
    -0.42
     ragaz
    -0.42
     odkazy
    -0.42
    POSITIVE LOGITS
    出版年
    0.64
    ModelSerializer
    0.59
    sizeCache
    0.59
    eleste
    0.56
     Benth
    0.54
     predeceased
    0.53
    dominal
    0.53
    HEAST
    0.53
     precipit
    0.52
     Stedman
    0.52
    Activations Density 0.084%

    No Known Activations