© 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. 4539
    Prev
    Next
    INDEX
    Explanations

    authorities

    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
    ỡng
    -0.52
     sä
    -0.47
    UVWXYZ
    -0.46
    protoimpl
    -0.45
    ++++++++++++++++
    -0.41
     verz
    -0.41
     Stardust
    -0.41
    crí
    -0.41
    Hochspringen
    -0.40
     quién
    -0.40
    POSITIVE LOGITS
     Roskov
    0.71
    UrlResolution
    0.66
    Hayes
    0.66
    //
    0.64
    mybatisplus
    0.62
    basicConfig
    0.61
     mergeFrom
    0.61
     Hayes
    0.60
    HtmlAttribute
    0.59
    adpleegd
    0.55
    Activations Density 0.000%

    No Known Activations