© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44017
    Prev
    Next
    INDEX
    Explanations

    connects

    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
     connected
    -1.24
    connected
    -1.17
    Connected
    -1.14
     Connected
    -1.11
     connecting
    -1.09
     connects
    -1.08
     conectado
    -1.03
     conectados
    -1.03
     connective
    -0.99
     Theſe
    -0.95
    POSITIVE LOGITS
     to
    0.75
     sub
    0.66
     
    0.57
     er
    0.56
    日閲覧
    0.52
     na
    0.51
     aus
    0.50
    DialogContent
    0.49
     no
    0.48
    ukul
    0.48
    Activations Density 0.587%

    No Known Activations