© 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. 44226
    Prev
    Next
    INDEX
    Explanations

    connected

    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
    -2.31
    connected
    -1.95
     Connected
    -1.80
    Connected
    -1.58
     conectado
    -1.38
     conectados
    -1.34
     disconnected
    -1.26
     connecté
    -1.21
     interconnected
    -1.20
     unconnected
    -1.14
    POSITIVE LOGITS
    SharedCtor
    0.64
    ness
    0.57
    en
    0.52
     '\\;'
    0.52
    ه
    0.52
    }))
    0.52
    ы
    0.51
    nat
    0.50
    VersionUID
    0.49
    INCREF
    0.49
    Activations Density 0.066%

    No Known Activations