© 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. 4564
    Prev
    Next
    INDEX
    Explanations

    places/positions

    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
     Bioaccumulative
    -0.62
    icose
    -0.57
    最快更新
    -0.53
     esternos
    -0.53
    Parcelize
    -0.52
    InitStruct
    -0.52
    漉
    -0.50
    batim
    -0.50
    المناصب
    -0.50
    ποίη
    -0.49
    POSITIVE LOGITS
     for
    1.14
    TagHelper
    0.69
    AnchorStyles
    0.68
    AccessorTable
    0.62
    verwijspagina
    0.61
    for
    0.60
     voor
    0.54
     near
    0.53
    ViewFeatures
    0.53
     für
    0.52
    Activations Density 0.001%

    No Known Activations