© 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. 4-CLT-HP
    7. 2163
    Prev
    Next
    INDEX
    Explanations

    com

    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
    hyrchwyd
    -0.75
    KommentareTeilen
    -0.75
    MLLoader
    -0.68
    DockStyle
    -0.65
    AndEndTag
    -0.64
     bale
    -0.62
     الرياضيه
    -0.60
    StateException
    -0.59
     ftate
    -0.58
    KeySpec
    -0.58
    POSITIVE LOGITS
    duğu
    0.54
     competed
    0.47
    textTheme
    0.47
     metales
    0.45
     nødvendig
    0.45
    numerusform
    0.44
    metis
    0.44
    chapel
    0.43
     Giro
    0.43
    ikations
    0.43
    Activations Density 0.005%

    No Known Activations