© 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. 5-CLT-HP
    7. 824
    Prev
    Next
    INDEX
    Explanations

    coding/forms/user input

    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
     récomp
    -0.59
     immédi
    -0.56
     prossima
    -0.51
     lontano
    -0.51
    存于互联网档案馆
    -0.51
     végét
    -0.50
     réunis
    -0.49
     debout
    -0.48
     negócio
    -0.48
     puissiez
    -0.47
    POSITIVE LOGITS
    ScopeManager
    0.69
    TagMode
    0.65
    XtraReports
    0.64
    InputTagHelper
    0.63
     guide
    0.63
    KURZBESCHREIBUNG
    0.60
     window
    0.59
     nakalista
    0.57
     propOrder
    0.56
    :✨
    0.55
    Activations Density 0.014%

    No Known Activations