© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10968
    Prev
    Next
    INDEX
    Explanations

    numbers dates times

    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
    CloseOperation
    -0.67
     Meksiku
    -0.66
     autorytatywna
    -0.66
     Италијани
    -0.65
     TAMBIÉN
    -0.64
     kasarigan
    -0.61
    DockStyle
    -0.58
    /*
    -0.57
     nahilalakip
    -0.56
    发表于
    -0.54
    POSITIVE LOGITS
     aku
    0.48
    apiVersion
    0.44
     ton
    0.43
    Gbps
    0.43
     m
    0.43
    टन
    0.43
     sie
    0.43
     bar
    0.42
     ki
    0.42
     “
    0.42
    Activations Density 0.004%

    No Known Activations