© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75873
    Prev
    Next
    INDEX
    Explanations

    events

    np_max-act-logits · 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
     Events
    -1.02
    Events
    -0.99
    events
    -0.91
     EVENTS
    -0.88
     events
    -0.84
     Conferences
    -0.84
     Festivals
    -0.78
    EVENTS
    -0.76
     Competitions
    -0.75
     conferences
    -0.71
    POSITIVE LOGITS
     shin
    0.57
    
    0.56
     function
    0.56
     propOrder
    0.53
    rungsseite
    0.53
     getUsers
    0.51
     get
    0.51
     knees
    0.49
     downvoted
    0.49
    bietern
    0.49
    Activations Density 0.003%

    No Known Activations