© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78228
    Prev
    Next
    INDEX
    Explanations

    Unstructured dataset strings

    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
    Negative Logits
    دانشنامهٔ
    -0.68
    VersionUID
    -0.65
    KommentareTeilen
    -0.63
     otomatig
    -0.60
    Enllaces
    -0.55
     AssemblyCompany
    -0.55
    EndGlobalSection
    -0.55
     newBuilder
    -0.55
    וויק
    -0.54
    InvalidProtocol
    -0.54
    POSITIVE LOGITS
    lapsingToolbar
    0.51
    raded
    0.50
     Flat
    0.50
     newState
    0.50
     flat
    0.47
     Witkin
    0.46
     GenerationType
    0.45
     FLAT
    0.45
     للمعارف
    0.45
     Stoll
    0.44
    Activations Density 0.001%

    No Known Activations