© 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. 20-CLT-HP
    7. 71767
    Prev
    Next
    INDEX
    Explanations

    Place or company abbreviations

    np_max-act-logits · 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
    taxia
    -0.54
    WebElementEntity
    -0.53
     Obispo
    -0.48
     akka
    -0.48
     bağlantılar
    -0.48
     mergeFrom
    -0.48
    abestanden
    -0.48
     Twe
    -0.47
    ష్
    -0.46
    piecze
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.64
     الحره
    0.59
    TagMode
    0.57
     متعلقه
    0.54
    complexContent
    0.51
     كومونز
    0.48
     ***!
    0.47
    +:+
    0.47
    ArgsConstructor
    0.47
    期刊论文
    0.46
    Activations Density 0.001%

    No Known Activations