© 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. 91201
    Prev
    Next
    INDEX
    Explanations

    collaboration

    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
     collaboration
    -2.25
     Collaboration
    -2.05
     collaborate
    -2.03
    Collaboration
    -1.97
    collaboration
    -1.96
     collaborations
    -1.93
     collaborative
    -1.88
     collaborating
    -1.84
     collaborated
    -1.80
     collabor
    -1.74
    POSITIVE LOGITS
     between
    0.62
    ist
    0.60
    ists
    0.52
    e
    0.51
    er
    0.50
    a
    0.49
     while
    0.48
    ,
    0.48
     in
    0.46
     and
    0.46
    Activations Density 0.072%

    No Known Activations