© 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. 45856
    Prev
    Next
    INDEX
    Explanations

    train

    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
     Train
    -0.58
    TRAIN
    -0.57
    Train
    -0.57
    Vorlage
    -0.57
     TRAIN
    -0.54
     παρά
    -0.54
     Chwiliwch
    -0.53
     Selecciona
    -0.53
    Express
    -0.53
    express
    -0.53
    POSITIVE LOGITS
    tagHelperRunner
    0.57
    FXMLLoader
    0.55
     defaultstate
    0.51
     betweenstory
    0.51
    beiros
    0.49
    DotNetBar
    0.48
    GenerationType
    0.47
     aapt
    0.47
    men
    0.47
    apunov
    0.47
    Activations Density 0.020%

    No Known Activations