© 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. 5-CLT-HP
    7. 6300
    Prev
    Next
    INDEX
    Explanations

    Formal texts/Internet content

    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
    Negative Logits
    enumii
    -0.63
    WebServlet
    -0.60
     <>",
    -0.56
    ves
    -0.55
     AssemblyTitle
    -0.54
    σμο
    -0.50
    WriteLiteral
    -0.50
     дописавши
    -0.49
    enumi
    -0.49
     Armas
    -0.49
    POSITIVE LOGITS
    SaveVideo
    0.63
    cadilly
    0.56
     morire
    0.55
    dialement
    0.54
     panoramique
    0.52
     Wikiseite
    0.51
    ubehör
    0.50
     chimiques
    0.50
    ADUATE
    0.49
    rašymas
    0.49
    Activations Density 0.000%

    No Known Activations