© 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. 98001
    Prev
    Next
    INDEX
    Explanations

    brach

    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
     defaultstate
    -0.78
    PyExc
    -0.66
    ViewImports
    -0.65
    Билгалдахарш
    -0.65
     otomatig
    -0.63
    脚注の使い方
    -0.63
    enumi
    -0.63
    UnusedPrivate
    -0.61
    //
    -0.60
    Geplaatst
    -0.59
    POSITIVE LOGITS
    ii
    0.57
     mii
    0.46
     judiciaire
    0.46
     marquées
    0.46
     totales
    0.45
     intérieure
    0.45
     essentielle
    0.45
     rosse
    0.44
     âme
    0.44
     lettore
    0.44
    Activations Density 0.001%

    No Known Activations