© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45273
    Prev
    Next
    INDEX
    Explanations

    bind

    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
     rush
    -1.41
     bind
    -1.30
     hurry
    -1.05
     dash
    -1.04
     Bind
    -0.99
     rushing
    -0.98
    rush
    -0.98
     Rush
    -0.95
     rushed
    -0.93
    asa
    -0.91
    POSITIVE LOGITS
    s
    0.59
     &___
    0.56
    soever
    0.56
     snippetHide
    0.55
    topf
    0.52
    omores
    0.52
    ships
    0.51
     становника
    0.50
    गी
    0.48
     sessionFactory
    0.48
    Activations Density 0.178%

    No Known Activations