© 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. 1-CLT-HP
    7. 13281
    Prev
    Next
    INDEX
    Explanations

    methods, techniques

    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
    Välislingid
    -0.65
     Lijst
    -0.65
     SCN
    -0.65
     nahilalakip
    -0.64
    LookAnd
    -0.64
     ſeveral
    -0.63
     TSC
    -0.61
     esternos
    -0.61
     ECR
    -0.61
    Билгалдахарш
    -0.60
    POSITIVE LOGITS
     propOrder
    0.49
     to
    0.41
     jackets
    0.40
    gheny
    0.40
    eth
    0.40
    NonQuery
    0.39
     ethyl
    0.38
     jacket
    0.38
    ExecuteNonQuery
    0.37
     for
    0.37
    Activations Density 0.022%

    No Known Activations