© 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. 4-CLT-HP
    7. 1458
    Prev
    Next
    INDEX
    Explanations

    to

    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
     fédé
    -0.67
     SwitchCompat
    -0.66
     énergé
    -0.63
     compréhension
    -0.63
     spécialisée
    -0.61
     traditionnels
    -0.61
     crainte
    -0.60
     néglig
    -0.60
     peur
    -0.59
     réguli
    -0.59
    POSITIVE LOGITS
    ContentAsync
    0.60
     الرياضيه
    0.55
     say
    0.54
    CloseOperation
    0.52
     remand
    0.52
     address
    0.52
     henvisninger
    0.50
     lenker
    0.49
     оригіналу
    0.48
     outline
    0.47
    Activations Density 0.010%

    No Known Activations