© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90440
    Prev
    Next
    INDEX
    Explanations

    position

    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
     فريبيس
    -0.84
    脚注の使い方
    -0.74
     position
    -0.71
     typelib
    -0.66
     positions
    -0.59
    EndGlobalSection
    -0.58
     dieß
    -0.57
    rungsseite
    -0.56
    idste
    -0.56
    position
    -0.55
    POSITIVE LOGITS
    autoconfigure
    0.57
    urlpatterns
    0.51
    Hochspringen
    0.51
     يتيمه
    0.50
     fea
    0.47
    mpty
    0.47
     of
    0.47
    internalType
    0.46
    ValueStyle
    0.46
    うち
    0.46
    Activations Density 0.014%

    No Known Activations