© 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. 1024
    Prev
    Next
    INDEX
    Explanations

    acquired, purchased

    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
     acquired
    -1.20
    acquired
    -1.10
     purchased
    -1.04
     adquirido
    -1.02
     bought
    -1.00
     attained
    -0.96
    GraphicsUnit
    -0.95
     Acquired
    -0.95
     received
    -0.94
     earned
    -0.94
    POSITIVE LOGITS
    ,
    0.69
     or
    0.69
     and
    0.67
     by
    0.66
     but
    0.66
     it
    0.65
    .
    0.65
     in
    0.62
     online
    0.61
     early
    0.60
    Activations Density 0.062%

    No Known Activations