© 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. 94388
    Prev
    Next
    INDEX
    Explanations

    "to be" verb forms

    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
     препратки
    -0.73
    keeps
    -0.58
    rungsseite
    -0.57
    évaluateur
    -0.57
     nahilalakip
    -0.56
     raps
    -0.56
    httphttps
    -0.53
     Walks
    -0.53
    ']")
    -0.53
     swims
    -0.52
    POSITIVE LOGITS
    +#+#
    0.56
    asgi
    0.54
    IVEREF
    0.50
    الإنجليزية
    0.46
     einiger
    0.45
    penup
    0.45
     active
    0.45
    newpage
    0.44
    ammlung
    0.44
    StackNavigator
    0.44
    Activations Density 0.004%

    No Known Activations