© 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. 92034
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    BeginContext
    -0.81
    MigrationBuilder
    -0.79
     estimés
    -0.71
    openzeppelin
    -0.71
    yntaxException
    -0.69
     gyhoeddwyd
    -0.69
    Hauptartikel
    -0.66
    FieldOffset
    -0.65
    ThroughAttribute
    -0.63
    prefixer
    -0.63
    POSITIVE LOGITS
     lèvres
    0.61
     legales
    0.59
     prisonniers
    0.58
     épaules
    0.56
     AssemblyCompany
    0.55
     sauvages
    0.55
     liné
    0.53
     équ
    0.52
     eiland
    0.52
     élevées
    0.51
    Activations Density 0.001%

    No Known Activations