© 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. 46160
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    Geplaatst
    -0.86
     مشين
    -0.79
     étoient
    -0.74
    ItemBackground
    -0.73
     feroit
    -0.73
     drôle
    -0.70
    Географиясе
    -0.70
    NameInMap
    -0.69
     auroit
    -0.69
     quelcon
    -0.68
    POSITIVE LOGITS
     obtain
    0.57
     have
    0.55
    typeparam
    0.53
     enter
    0.50
     make
    0.50
     receive
    0.50
     explain
    0.49
     get
    0.47
     estekak
    0.47
     perform
    0.46
    Activations Density 0.006%

    No Known Activations