© 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. 0-CLT-HP
    7. 90728
    Prev
    Next
    INDEX
    Explanations

    nup

    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
    nup
    -1.50
     nup
    -0.70
     Efq
    -0.69
    клопе
    -0.68
    NavController
    -0.66
     Houſe
    -0.66
     Normdatei
    -0.65
     houſe
    -0.65
    PreferredItem
    -0.61
     eorum
    -0.60
    POSITIVE LOGITS
    ti
    0.52
     nakalista
    0.48
    tual
    0.48
     snippetHide
    0.44
    Πηγές
    0.43
    {#
    0.42
    Lähteet
    0.42
    rairie
    0.42
    t
    0.41
     nawr
    0.41
    Activations Density 0.124%

    No Known Activations