© 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. 0-CLT-HP
    7. 42184
    Prev
    Next
    INDEX
    Explanations

    {

    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
    Jereo
    -0.59
    Hentet
    -0.58
    expandindo
    -0.56
     pleg
    -0.52
    ResumeLayout
    -0.52
     protoimpl
    -0.51
     مشين
    -0.51
     stocking
    -0.50
    indépendance
    -0.50
     chré
    -0.50
    POSITIVE LOGITS
     Bunt
    0.59
     OGS
    0.57
     Forumite
    0.57
    URLException
    0.55
     chi̍t
    0.54
     Wiktionnaire
    0.54
     gari
    0.53
     bisect
    0.53
     Arbit
    0.51
     Galo
    0.51
    Activations Density 0.134%

    No Known Activations