© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 529
    Prev
    Next
    INDEX
    Explanations

    ies

    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
     الدولى
    -0.50
     forgiven
    -0.48
    yntaxException
    -0.47
    (!__
    -0.46
    vode
    -0.45
    trás
    -0.45
     exceso
    -0.45
     DBNull
    -0.45
    Espèce
    -0.45
     vied
    -0.44
    POSITIVE LOGITS
    MigrationBuilder
    0.63
     insuffisamment
    0.59
     time
    0.57
     disambiguazione
    0.56
    verwijspagina
    0.56
    المكان
    0.55
     muualla
    0.55
     BrowserModule
    0.55
    bbat
    0.54
    ecap
    0.54
    Activations Density 0.002%

    No Known Activations