© 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. 91102
    Prev
    Next
    INDEX
    Explanations

    desire

    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
     desired
    -1.45
    desired
    -1.17
     deseado
    -0.96
     Desired
    -0.90
     desirable
    -0.82
     gewüns
    -0.82
     required
    -0.81
    wanted
    -0.80
     desiring
    -0.77
    Desired
    -0.77
    POSITIVE LOGITS
     outcome
    0.66
     result
    0.64
     level
    0.54
     behavior
    0.54
     Outcome
    0.53
     lifetime
    0.52
     pure
    0.51
    LY
    0.50
     Result
    0.50
    outcome
    0.50
    Activations Density 0.033%

    No Known Activations